Language Model Behavior: A Comprehensive Survey
Open accessThe DOI matches its Crossref record; 425 of the 425 references it cites were found in a registry or an index.
Abstract
Transformer language models have received widespread public attention, yet their generated text is often surprising even to NLP researchers. In this survey, we discuss over 250 recent studies of English language model behavior before task-specific fine-tuning. Language models possess basic capabilities in syntax, semantics, pragmatics, world knowledge, and reasoning, but these capabilities are sensitive to specific inputs and surface features. Despite dramatic increases in generated text quality as models scale to hundreds of billions of parameters, the models are still prone to unfactual responses, commonsense errors, memorized text, and social biases. Many of these weaknesses can be framed as over-generalizations or under-generalizations of learned patterns in text. We synthesize recent results to highlight what is currently known about large language model capabilities, thus providing a resource for applied work and for research in adjacent fields that use language models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“So far, quantitative comparisons have looked mainly at basic grammar and syntax (5) or features such as word choice, punctuation, sentence length, and so on, finding evidence of some differences between human- and LLM-written text (10–14).”
From Do LLMs write like humans? Variation in grammatical and rhetorical styles (2025) · cites this paper as [5]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“Transformer language models have revolutionized the field of natural language processing (NLP) since their introduction in 2018 (Radford et al. 2018; Devlin et al. 2019).”
BackgroundMethodLanguage Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Grice, H. P. (1975) · Speech Acts · doi:10.1163/9789004368811_003 · Cited by 23,221
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“increases, the number of pre-training tokens should increase roughly proportionally (Kaplan et al. 2020; Hoffmann et al. 2022).”
BackgroundOn the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Energy and Policy Considerations for Deep Learning in NLP
Strubell, E., Ganesh, A., & McCallum, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1355 · Cited by 3,684
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1101 · Cited by 3,342
Transformer-XL: Attentive language models beyond a fixed-length context
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1285 · Cited by 3,169
Training Language Models to Follow Instructions with Human Feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2011 · Cited by 3,117
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092
BERTScore: Evaluating Text Generation with BERT
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09675 · Cited by 2,865
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
Self-Attention with Relative Position Representations
Shaw, P., Uszkoreit, J., & Vaswani, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2074 · Cited by 2,505
Large language models are zero-shot reasoners
Kojima, T., Gu, S. (., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1613 · Cited by 2,013 · cited 1×
“can be prompted with a simple “Let’s think step by step” to produce valid reasoning (i.e. “chain-of-thought prompting”; Kojima et al. 2022).”
BackgroundLarge Language Models are Zero-Shot Reasoners
Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11916 · Cited by 2,013 · cited 1×
“can be prompted with a simple “Let’s think step by step” to produce valid reasoning (i.e. “chain-of-thought prompting”; Kojima et al. 2022).”
Background(2011) · IEEE Software · doi:10.1109/ms.2011.67 · Cited by 1,989
Jain, S., & Wallace, B. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1357 · Cited by 1,987
RoFormer: Enhanced transformer with rotary position embedding
Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., & Liu, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2023.127063 · Cited by 1,957
Robust Speech Recognition via Large-Scale Weak Supervision
Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2022) · arXiv · doi:10.48550/arxiv.2212.04356 · Cited by 1,953 · cited 1×
“2021), speech models (Lakhotia et al. 2021; Radford et al. 2022), knowledge-augmented models (Zhang et al.”
BackgroundRoFormer: Enhanced Transformer with Rotary Position Embedding
Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., & Liu, Y. (2021) · arXiv · doi:10.48550/arxiv.2104.09864 · Cited by 1,952
Language Models as Knowledge Bases?
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1250 · Cited by 1,834 · cited 1×
“countries and locations, popular products, historical figures, and even genres of books, movies, and music (Petroni et al. 2019; Penha and Hauff 2020).”
BackgroundProceedings for the Annual Meeting of the Cognitive Science Society
Dziemianko, M., Clarke, A. D. F., & Keller, F. (2013) · Cited by 1,726
A primer in BERTology: What we know about how BERT works
Rogers, A., Kovaleva, O., & Rumshisky, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00349 · Cited by 1,552
ERNIE: Enhanced Language Representation with Informative Entities
Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., & Liu, Q. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1139 · Cited by 1,482 · cited 1×
“2022), knowledge-augmented models (Zhang et al. 2019), sparselyactivated models (Fedus, Zoph, and Shazeer 2022), or compressed models (Sanh et al.”
BackgroundEvaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436
What Does BERT Look at? An Analysis of BERT’s Attention
Clark, K., Khandelwal, U., Levy, O., & Manning, C. D. (2019) · Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w19-4828 · Cited by 1,373 · cited 1×
“inter-token relationships (Clark et al. 2019; Kovaleva et al. 2019; Vig and Belinkov 2019), although the attention weights do not necessarily influence language modeling predic-”
BackgroundBERT Rediscovers the Classical NLP Pipeline
Tenney, I., Das, D., & Pavlick, E. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1452 · Cited by 1,307
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304
Emergent Abilities of Large Language Models
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.07682 · Cited by 1,264
In-context Learning and Induction Heads
Olsson, C., Elhage, N., Nanda, N., Joseph, N., DasSarma, N., Henighan, T., Mann, B., Askell, A., Bai, Y., Chen, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.11895 · Cited by 1,170
Toolformer: Language Models Can Teach Themselves to Use Tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv · doi:10.48550/arxiv.2302.04761 · Cited by 1,150
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101 · cited 2×
“2022) or examples of outputs that correctly follow input instructions (Wei et al. 2022a; Iyer et al. 2022).”
BackgroundClimbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
Bender, E. M., & Koller, A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.463 · Cited by 1,082
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. R. (2019) · arXiv · doi:10.48550/arxiv.1905.00537 · Cited by 1,051 · cited 1×
“marks and on open-ended natural language generation tasks from the general public (Wang et al. 2019; Johnson 2022).”
BackgroundLanguage (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050 · cited 2×
“2022); for example, social biases can be analyzed along multiple dimensions, and their effects depend on the communities and power relations involved (Blodgett et al. 2020).”
BackgroundSubword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates
Kudo, T. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1007 · Cited by 1,021
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Fedus, W., Zoph, B., & Shazeer, N. (2021) · arXiv · doi:10.48550/arxiv.2101.03961 · Cited by 1,005
How Can We Know What Language Models Know?
Jiang, Z., Xu, F. F., Araki, J., & Neubig, G. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00324 · Cited by 1,002
Neural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
McCoy, R. T., Pavlick, E., & Linzen, T. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1334 · Cited by 944
Training Compute-Optimal Large Language Models
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2176 · Cited by 932
Training Compute-Optimal Large Language Models
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.15556 · Cited by 929
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Lin, S., Hilton, J., & Evans, O. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.229 · Cited by 904
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Lin, S., Hilton, J., & Evans, O. (2021) · arXiv · doi:10.48550/arxiv.2109.07958 · Cited by 899
Predicting pragmatic reasoning in language games
Frank, M. C., & Goodman, N. D. (2012) · Science · doi:10.1126/science.1218633 · Cited by 868
Out of One, Many: Using Language Models to Simulate Human Samples
Argyle, L. P., Busby, E. C., Fulda, N., Gubler, J. R., Rytting, C., & Wingate, D. (2023) · Political Analysis · doi:10.1017/pan.2023.2 · Cited by 783 · cited 2×
“that person, and it even predicts similar voting patterns and multiple choice responses to political surveys (Argyle et al. 2023).”
BackgroundLaMDA: Language Models for Dialog Applications
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T., Baker, L., Du, Y., et al. (2022) · arXiv · doi:10.48550/arxiv.2201.08239 · Cited by 778
The State and Fate of Linguistic Diversity and Inclusion in the NLP World
Joshi, P., Santy, S., Budhiraja, A., Bali, K., & Choudhury, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.560 · Cited by 766
Taxonomy of Risks posed by Language Models
Weidinger, L., Uesato, J., Rauh, M., Griffin, C., Huang, P.-S., Mellor, J., Glaese, A., Cheng, M., Balle, B., Kasirzadeh, A., et al. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533088 · Cited by 764
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.759 · Cited by 755 · cited 1×
“incorrect answers; examples in few-shot prompting primarily allow the models to learn the set of possible answers and the general input format (Min et al. 2022).”
BackgroundRethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2022) · arXiv · doi:10.48550/arxiv.2202.12837 · Cited by 752 · cited 1×
“incorrect answers; examples in few-shot prompting primarily allow the models to learn the set of possible answers and the general input format (Min et al. 2022).”
BackgroundEvaluating large language models trained on code
Chen, M. (2024) · TIB Data Manager · doi:10.57702/wbv3e61b · Cited by 737
Syntax: A Generative Introduction
Carnie, A. (2002) · Cited by 735
Extracting Training Data from Large Language Models
Carlini, N., Tramer, F., Wallace, E., Jagielski, M., Herbert-Voss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, U., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.07805 · Cited by 727
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Gehman, S., Gururangan, S., Sap, M., Choi, Y., & Smith, N. A. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.301 · Cited by 693
Serrano, S., & Smith, N. A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1282 · Cited by 690
StereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.416 · Cited by 643
StereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2020) · arXiv · doi:10.48550/arxiv.2004.09456 · Cited by 643
Universal Adversarial Triggers for Attacking and Analyzing NLP
Wallace, E., Feng, S., Kandpal, N., Gardner, M., & Singh, S. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1221 · Cited by 642 · cited 1×
“Automated prompt construction methods can identify input text prompts that induce racist outputs and hate speech (Wallace et al. 2019a), controversial opinions”
BackgroundBeyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.04615 · Cited by 569
Using cognitive psychology to understand GPT-3
Binz, M., & Schulz, E. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2218523120 · Cited by 559
The Woman Worked as a Babysitter: On Biases in Language Generation
Sheng, E., Chang, K.-W., Natarajan, P., & Peng, N. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1339 · Cited by 537 · cited 1×
“2020), sentences about black or gay people (Sheng et al. 2019), or sentences about nonbinary, disabled, or”
BackgroundWhat BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models
Ettinger, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00298 · Cited by 511
Revealing the Dark Secrets of BERT
Kovaleva, O., Romanov, A., Rogers, A., & Rumshisky, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1445 · Cited by 495 · cited 1×
“inter-token relationships (Clark et al. 2019; Kovaleva et al. 2019; Vig and Belinkov 2019), although the attention weights do not necessarily influence language modeling predic-”
BackgroundEthical and social risks of harm from Language Models
Weidinger, L., Mellor, J., Rauh, M., Griffin, C., Uesato, J., Huang, P.-S., Cheng, M., Glaese, M., Balle, B., Kasirzadeh, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.04359 · Cited by 477
Persistent Anti-Muslim Bias in Large Language Models
Abid, A., Farooqi, M., & Zou, J. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462624 · Cited by 476
Poverty of the Stimulus Revisited
Berwick, R. C., Pietroski, P., Yankama, B., & Chomsky, N. (2011) · Cognitive Science · doi:10.1111/j.1551-6709.2011.01189.x · Cited by 447
CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
Nangia, N., Vania, C., Bhalerao, R., & Bowman, S. R. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.154 · Cited by 446
Zafrir, O., Boudoukh, G., Izsak, P., & Wasserblat, M. (2019) · 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS) · doi:10.1109/emc2-nips53020.2019.00016 · Cited by 442
(2021) · International Conference on Learning Representations · Cited by 435
Opt: Open pre-trained transformer language models
Zhang, S. (2025) · TIB Data Manager · doi:10.57702/dn0pmcbs · Cited by 405
Emergent analogical reasoning in large language models
Webb, T., Holyoak, K. J., & Lu, H. (2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01659-w · Cited by 404
Assessing BERT's Syntactic Abilities
Goldberg, Y. (2019) · arXiv · doi:10.48550/arxiv.1901.05287 · Cited by 385
Improving language models by retrieving from trillions of tokens
Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., Driessche, G. V. D., Lespiau, J.-B., Damoc, B., Clark, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.04426 · Cited by 382
Red Teaming Language Models with Language Models
Perez, E., Huang, S., Song, F., Cai, T., Ring, R., Aslanides, J., Glaese, A., McAleese, N., & Irving, G. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.225 · Cited by 363
(2020) · International Conference on Machine Learning · Cited by 358
Transformer Feed-Forward Layers Are Key-Value Memories
Geva, M., Schuster, R., Berant, J., & Levy, O. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.446 · Cited by 353 · cited 1×
“entries in the models’ vector representations) and language modeling predictions (Vig et al. 2020; Geva et al. 2021; Finlayson et al. 2021; Geva et al. 2022).”
BackgroundTransformer Feed-Forward Layers Are Key-Value Memories
Geva, M., Schuster, R., Berant, J., & Levy, O. (2020) · arXiv · doi:10.48550/arxiv.2012.14913 · Cited by 353
Measuring Bias in Contextualized Word Representations
Kurita, K., Vyas, N., Pareek, A., Black, A. W., & Tsvetkov, Y. (2019) · Proceedings of the First Workshop on Gender Bias in Natural Language Processing · doi:10.18653/v1/w19-3823 · Cited by 348 · cited 1×
“negative sentiment completions only sometimes exhibits bias effects in masked and autoregressive models (Kurita et al. 2019; Silva, Tambwekar, and Gombolay 2021).”
BackgroundHuman heuristics for AI-generated language are flawed
Jakesch, M., Hancock, J. T., & Naaman, M. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2208839120 · Cited by 342
The debate over understanding in AI’s large language models
Mitchell, M., & Krakauer, D. C. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2215907120 · Cited by 340
Mallen, A., Asai, A., Zhong, V., Das, R., Khashabi, D., & Hajishirzi, H. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.546 · Cited by 340
Situation models, mental simulations, and abstract concepts in discourse comprehension
Zwaan, R. A. (2016) · Psychonomic Bulletin & Review · doi:10.3758/s13423-015-0864-x · Cited by 330
Predictability and Surprise in Large Generative Models
Ganguli, D., Hernandez, D., Lovitt, L., DasSarma, N., Henighan, T., Jones, A., Joseph, N., Kernion, J., Mann, B., Askell, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2202.07785 · Cited by 324
A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models
Zhang, H., Song, H., Li, S., Zhou, M., & Song, D. (2024) · ACM Computing Surveys · doi:10.1145/3617680 · Cited by 317 · cited 1×
“data using controlled text generation (Li et al. 2021; Zhang et al. 2023a).”
Measuring Mathematical Problem Solving With the MATH Dataset
Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., & Steinhardt, J. (2021) · arXiv · doi:10.48550/arxiv.2103.03874 · Cited by 306 · cited 1×
“Autoregressive models perform poorly (<10% accuracy) on competition math problems, even with fine-tuning (Hendrycks et al. 2021b).”
MethodDeduplicating Training Data Makes Language Models Better
Lee, K., Ippolito, D., Nystrom, A., Zhang, C., Eck, D., Callison-Burch, C., & Carlini, N. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.577 · Cited by 304
Measuring and Narrowing the Compositionality Gap in Language Models
Press, O., Zhang, M., Min, S., Schmidt, L., Smith, N., & Lewis, M. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.378 · Cited by 303
Analyzing the Structure of Attention in a Transformer Language Model
Vig, J., & Belinkov, Y. (2019) · Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w19-4808 · Cited by 301
Measuring and Narrowing the Compositionality Gap in Language Models
Press, O., Zhang, M., Min, S., Schmidt, L., Smith, N. A., & Lewis, M. (2022) · arXiv · doi:10.48550/arxiv.2210.03350 · Cited by 294
All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text
Clark, E., August, T., Serrano, S., Haduong, N., Gururangan, S., & Smith, N. A. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.565 · Cited by 290
All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text
Clark, E., August, T., Serrano, S., Haduong, N., Gururangan, S., & Smith, N. A. (2021) · arXiv · doi:10.48550/arxiv.2107.00061 · Cited by 290
Beam Search Strategies for Neural Machine Translation
Freitag, M., & Al-Onaizan, Y. (2017) · Proceedings of the First Workshop on Neural Machine Translation · doi:10.18653/v1/w17-3207 · Cited by 286
Smith, S., Patwary, M., Norick, B., LeGresley, P., Rajbhandari, S., Casper, J., Liu, Z., Prabhumoye, S., Zerveas, G., Korthikanti, V., et al. (2022) · arXiv · doi:10.48550/arxiv.2201.11990 · Cited by 286
Generalization through Memorization: Nearest Neighbor Language Models
Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., & Lewis, M. (2019) · arXiv · doi:10.48550/arxiv.1911.00172 · Cited by 285
Commonsense Knowledge Mining from Pretrained Models
Davison, J., Feldman, J., & Rush, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1109 · Cited by 264
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.164 · Cited by 264 · cited 1×
“quences (Ippolito et al. 2020), but even when provided with specialized instructions and examples, people only reach about 55% accuracy (Clark et al.”
BackgroundAutomatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2019) · arXiv · doi:10.48550/arxiv.1911.00650 · Cited by 264 · cited 1×
“quences (Ippolito et al. 2020), but even when provided with specialized instructions and examples, people only reach about 55% accuracy (Clark et al.”
BackgroundChallenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
Suzgun, M., Scales, N., Schärli, N., Gehrmann, S., Tay, Y., Chung, H. W., Chowdhery, A., Le, Q., Chi, E., Zhou, D., et al. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.824 · Cited by 253
Probing Classifiers: Promises, Shortcomings, and Advances
Belinkov, Y. (2022) · Computational Linguistics · doi:10.1162/coli_a_00422 · Cited by 249
BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
Dhamala, J., Sun, T., Kumar, V., Krishna, S., Pruksachatkun, Y., Chang, K.-W., & Gupta, R. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445924 · Cited by 244 · cited 1×
“explicitly, such as when using names from Wikipedia matching different identity groups (Dhamala et al. 2021).”
BackgroundHagendorff, T., Fabi, S., & Kosinski, M. (2023) · Nature Computational Science · doi:10.1038/s43588-023-00527-x · Cited by 243
AI model GPT-3 (dis)informs us better than humans
Spitale, G., Biller-Andorno, N., & Germani, F. (2023) · Science Advances · doi:10.1126/sciadv.adh1850 · Cited by 241
A taxonomy and review of generalization research in NLP
Hupkes, D., Giulianelli, M., Dankers, V., Artetxe, M., Elazar, Y., Pimentel, T., Christodoulopoulos, C., Lasri, K., Saphra, N., Sinclair, A., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00729-y · Cited by 241
Are All Languages Created Equal in Multilingual BERT?
Wu, S., & Dredze, M. (2020) · Proceedings of the 5th Workshop on Representation Learning for NLP · doi:10.18653/v1/2020.repl4nlp-1.16 · Cited by 234
Locating and Editing Factual Associations in GPT
Meng, K., Bau, D., Andonian, A., & Belinkov, Y. (2022) · arXiv · doi:10.48550/arxiv.2202.05262 · Cited by 230 · cited 1×
“Parameter-level interventions can modify factual associations in language models in targeted ways (Meng et al. 2022),”
BackgroundDo NLP Models Know Numbers? Probing Numeracy in Embeddings
Wallace, E., Wang, Y., Li, S., Singh, S., & Gardner, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1534 · Cited by 227
Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly
Kassner, N., & Schütze, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.698 · Cited by 223
Measuring and improving consistency in pretrained language models
Elazar, Y., Kassner, N., Ravfogel, S., Ravichander, A., Hovy, E., Schütze, H., & Goldberg, Y. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00410 · Cited by 220 · cited 1×
“Accuracies in both masked and autoregressive models vary substantially when the templates are paraphrased (Elazar et al. 2021; Cao et al. 2022) or altered in terms of punctuation (Podkorytov, Bis, and Liu 2021).”
BackgroundTransformer Language Models without Positional Encodings Still Learn Positional Information
Haviv, A., Ram, O., Press, O., Izsak, P., & Levy, O. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.99 · Cited by 220
Mallen, A. T., Asai, A., Zhong, V., Das, R., Hajishirzi, H., & Khashabi, D. (2022) · arXiv.org · doi:10.48550/arxiv.2212.10511 · Cited by 214 · cited 1×
“for popular entities, as measured by Wikipedia views (Mallen et al. 2022).”
BackgroundPredictability and Surprise in Large Generative Models
Ganguli, D., Hernandez, D., Lovitt, L., Askell, A., Bai, Y., Chen, A., Conerly, T., Dassarma, N., Drain, D., Elhage, N., et al. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533229 · Cited by 207
Quantifying Memorization Across Neural Language Models
Carlini, N., Ippolito, D., Jagielski, M., Lee, K., Tramer, F., & Zhang, C. (2022) · arXiv · doi:10.48550/arxiv.2202.07646 · Cited by 204 · cited 2×
“generate the memorized continuation (Lee et al. 2022; Carlini et al. 2023), and examples that appear more frequently in the pre-training corpus are more likely to be memorized”
BackgroundIsotropy in the Contextual Embedding Space: Clusters and Manifolds
Cai, X., Huang, J., Bian, Y., & Church, K. (2021) · International Conference on Learning Representations · Cited by 195
A Watermark for Large Language Models
Kirchenbauer, J., Geiping, J., Wen, Y., Katz, J., Miers, I., & Goldstein, T. (2023) · arXiv · doi:10.48550/arxiv.2301.10226 · Cited by 194 · cited 1×
“posed “watermarking” model-generated text by slightly increasing the probabilities of “whitelist” tokens during text generation (Kirchenbauer et al. 2023), or by explicitly replacing some tokens with whitelist tokens (He et al.”
BackgroundDiscovering Language Model Behaviors with Model-Written Evaluations
Perez, E., Ringer, S., Lukosiute, K., Nguyen, K., Chen, E., Heiner, S., Pettit, C., Olsson, C., Kundu, S., Kadavath, S., et al. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.847 · Cited by 194
A Survey of Vision-Language Pre-Trained Models
Du, Y., Liu, Z., Li, J., & Zhao, W. X. (2022) · Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/762 · Cited by 190
Language Models (Mostly) Know What They Know
Kadavath, S., Conerly, T., Askell, A., Henighan, T., Drain, D., Perez, E., Schiefer, N., Hatfield-Dodds, Z., DasSarma, N., Tran-Johnson, E., et al. (2022) · arXiv · doi:10.48550/arxiv.2207.05221 · Cited by 187
Sinha, K., Jia, R., Hupkes, D., Pineau, J., Williams, A., & Kiela, D. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.230 · Cited by 181
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
Jin, Z., Levine, S., Adauto, F. G., Kamal, O., Sap, M., Sachan, M., Mihalcea, R. F., Tenenbaum, J. B., & Schölkopf, B. (2022) · neural information processing systems · doi:10.52202/068431-2063 · Cited by 177
Position Information in Transformers: An Overview
Dufter, P., Schmitt, M., & Schütze, H. (2022) · Computational Linguistics · doi:10.1162/coli_a_00445 · Cited by 175
Theoretical Limitations of Self-Attention in Neural Sequence Models
Hahn, M. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00306 · Cited by 165
What Does it Mean for a Language Model to Preserve Privacy?
Brown, H., Lee, K., Mireshghallah, F., Shokri, R., & Tramèr, F. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3534642 · Cited by 165 · cited 1×
“ing on web text data; privacy expectations fluctuate, and information on the web is often intended for specific in-groups that the pre-training data does not distinguish (Brown et al. 2022).”
BackgroundAnalyzing Transformers in Embedding SpacePreprint
Dar, G., Geva, M., Gupta, A., & Berant, J. (2022) · Annual Meeting of the Association for Computational Linguistics · doi:10.48550/arxiv.2209.02535 · Cited by 163 · cited 1×
“interpreted using the same projections (Dar et al. 2022).”
Just Say No to Single Embeddings: Why Your AI Needs Multiple Perspectives
Coenen, A., Reif, E., Yuan, A., Kim, B., Pearce, A., Viégas, F., & WATTENBERG, M. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.02715 · Cited by 163
Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
Aher, G., Arriaga, R. I., & Kalai, A. T. (2022) · arXiv · doi:10.48550/arxiv.2208.10264 · Cited by 161
Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
Press, O., Smith, N. A., & Lewis, M. (2021) · arXiv · doi:10.48550/arxiv.2108.12409 · Cited by 161 · cited 1×
“Caesar?”) does not improve substantially (Press et al. 2022).”
Automatic Detection of Machine Generated Text: A Critical Survey
Jawahar, G., Abdul-Mageed, M., & Lakshmanan, V. S. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.208 · Cited by 156
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers
Lees, A., Tran, V. Q., Tay, Y., Sorensen, J., Gupta, J., Metzler, D., & Vasserman, L. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539147 · Cited by 155 · cited 1×
“These outputs can often be identified by human raters or automated systems (Jigsaw 2017; Welbl et al. 2021; Lees et al. 2022).”
BackgroundWhy Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers
Dai, D., Sun, Y., Dong, L., Hao, Y., Ma, S., Sui, Z., & Wei, F. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.247 · Cited by 154
Locating and Editing Factual Associations in GPT
Meng, K., Bau, D., Andonian, A., & Belinkov, Y. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1262 · Cited by 149 · cited 1×
“Parameter-level interventions can modify factual associations in language models in targeted ways (Meng et al. 2022),”
BackgroundWhat exactly is Universal Grammar, and has anyone seen it?
Dąbrowska, E. (2015) · Frontiers in Psychology · doi:10.3389/fpsyg.2015.00852 · Cited by 148
Should You Mask 15% in Masked Language Modeling?
Wettig, A., Gao, T., Zhong, Z., & Chen, D. (2023) · Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.217 · Cited by 145
Large Language Models Struggle to Learn Long-Tail Knowledge
Kandpal, N., Deng, H., Roberts, A., Wallace, E., & Raffel, C. (2022) · arXiv · doi:10.48550/arxiv.2211.08411 · Cited by 143 · cited 1×
“ments in the pre-training corpus; removing the relevant documents during pre-training decreases performance for the fact (Kandpal et al. 2022).”
Backgroundminicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language ModelsPreprint
Misra, K. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13112 · Cited by 142
Can language models learn from explanations in context?
Lampinen, A., Dasgupta, I., Chan, S., Mathewson, K., Tessler, M., Creswell, A., McClelland, J., Wang, J., & Hill, F. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022 · doi:10.18653/v1/2022.findings-emnlp.38 · Cited by 142
(2020) · neural information processing systems · Cited by 142
A Systematic Assessment of Syntactic Generalization in Neural Language Models
Hu, J., Gauthier, J., Qian, P., Wilcox, E., & Levy, R. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.158 · Cited by 134
Large Language Models Can Be Easily Distracted by Irrelevant Context
Shi, F., Chen, X., Misra, K., Scales, N., Dohan, D., Chi, E., Schärli, N., & Zhou, D. (2023) · arXiv · doi:10.48550/arxiv.2302.00093 · Cited by 134 · cited 1×
“irrelevant context (Shi et al. 2023), and similar to people, reinforcement-learning-tuned”
BackgroundA Systematic Investigation of Commonsense Knowledge in Large Language Models
Li, X. L., Kuncoro, A., Hoffmann, J., d’Autume, C. D. M., Blunsom, P., & Nematzadeh, A. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.812 · Cited by 133
The Geometry of Multilingual Language Model Representations
Chang, T. A., Tu, Z., & Bergen, B. K. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.9 · Cited by 133
Self-citationOn Position Embeddings in BERT
Wang, B., Shang, L., Lioma, C., Jiang, X., Yang, H., Liu, Q., & Simonsen, J. G. (2021) · Research at the University of Copenhagen (University of Copenhagen) · Cited by 133
Societal Biases in Language Generation: Progress and Challenges
Sheng, E., Chang, K.-W., Natarajan, P., & Peng, N. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.330 · Cited by 131
An Analysis of Natural Language Inference Benchmarks through the Lens of Negation
Hossain, M. M., Kovatchev, V., Dutta, P., Kao, T. H., Wei, E., & Blanco, E. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.732 · Cited by 130
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
Ganguli, D., Lovitt, L., Kernion, J., Askell, A., Bai, Y., Kadavath, S., Mann, B., Perez, E., Schiefer, N., Ndousse, K., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.07858 · Cited by 130
Testing the Ability of Language Models to Interpret Figurative Language
Liu, E., Cui, C., Zheng, K., & Neubig, G. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.330 · Cited by 125
Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies
Dev, S., Monajatipoor, M., Ovalle, A., Subramonian, A., Phillips, J., & Chang, K.-W. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.150 · Cited by 123
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
Wang, B., Min, S., Deng, X., Shen, J., Wu, Y., Zettlemoyer, L., & Sun, H. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.153 · Cited by 120
Bechtel, W., & Shagrir, O. (2015) · Topics in Cognitive Science · doi:10.1111/tops.12141 · Cited by 119
Pretrained Language Model for Text Generation: A Survey
Li, J., Tang, T., Zhao, W. X., & Wen, J.-R. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/612 · Cited by 118
Dou, Y., Forbes, M., Koncel-Kedziorski, R., Smith, N., & Choi, Y. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.501 · Cited by 118
Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs
Sap, M., Le Bras, R., Fried, D., & Choi, Y. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.248 · Cited by 118
Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs
Sap, M., LeBras, R., Fried, D., & Choi, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.13312 · Cited by 118 · cited 1×
“Indeed, when asked directly, GPT-3 can infer the knowledge and desires of characters in text (Summers-Stay, Bonial, and Voss 2021; Sap et al. 2022), and it can explain why characters perform actions in everyday situations based on common-”
BackgroundLin, B. Y., Lee, S., Khanna, R., & Ren, X. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.557 · Cited by 117
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
Geva, M., Caciularu, A., Wang, K., & Goldberg, Y. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.3 · Cited by 117
BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?
Ushio, A., Espinosa-Anke, L., Schockaert, S., & Camacho-Collados, J. (2021) · doi:10.18653/v1/2021.acl-long.280 · Cited by 116 · cited 1×
““X is to Y as Z is to _”) reasonably well (Ushio et al. 2021), but they perform significantly worse for more abstract and unconventional”
BackgroundChallenges in Detoxifying Language Models
Welbl, J., Glaese, A., Uesato, J., Dathathri, S., Mellor, J., Hendricks, L. A., Anderson, K., Kohli, P., Coppin, B., & Huang, P.-S. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.210 · Cited by 112
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
Meade, N., Poole-Dayan, E., & Reddy, S. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.132 · Cited by 110
A Recipe for Arbitrary Text Style Transfer with Large Language Models
Reif, E., Ippolito, D., Yuan, A., Coenen, A., Callison-Burch, C., & Wei, J. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/2022.acl-short.94 · Cited by 109
Event knowledge in large language models: the gap between the impossible and the unlikelyPreprint
Kauf, C., Ivanova, A. A., Rambelli, G., Chersoni, E., She, J. S., Chowdhury, Z., Fedorenko, E., & Lenci, A. (2022) · Cognitive Sciences · doi:10.48550/arxiv.2212.01488 · Cited by 108 · cited 2×
“Language models pass through both of these stages during pre-training (Chang and Bergen 2022).”
BackgroundFricke, S. (2018) · Journal of the Medical Library Association · doi:10.5195/jmla.2018.280 · Cited by 104
Language Model Evaluation Beyond Perplexity
Meister, C., & Cotterell, R. (2021) · doi:10.18653/v1/2021.acl-long.414 · Cited by 102
Are Large Pre-Trained Language Models Leaking Your Personal Information?
Huang, J., Shao, H., & Chang, K. C.-C. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022 · doi:10.18653/v1/2022.findings-emnlp.148 · Cited by 102
Linguistic Profiling of a Neural Language Model
Miaschi, A., Brunato⋄, D., Dell’Orletta⋄, F., & Venturi⋄, G. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.65 · Cited by 99 · cited 1×
“syntactic and semantic information learned during the original pre-training process (Miaschi et al. 2020; Mosbach et al. 2020).”
BackgroundThe Annual Meeting of the Cognitive Science Society
(2005) · Cognitive Systems Research · doi:10.1016/j.cogsys.2005.02.002 · Cited by 99
Challenges and Strategies in Cross-Cultural NLP
Hershcovich, D., Frank, S., Lent, H., de Lhoneux, M., Abdou, M., Brandl, S., Bugliarello, E., Cabello Piqueras, L., Chalkidis, I., Cui, R., et al. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.482 · Cited by 99
Do Large Language Models Know What Humans Know?
Trott, S., Jones, C., Chang, T., Michaelov, J., & Bergen, B. (2023) · Cognitive Science · doi:10.1111/cogs.13309 · Cited by 99
Self-citationInverse scaling can become U-shapedPreprint
Wei, J., Kim, N., Tay, Y., & Le, Q. V. (2022) · Conference on Empirical Methods in Natural Language Processing · doi:10.48550/arxiv.2211.02011 · Cited by 99 · cited 1×
“or subtask that medium-sized models learn, but that large models can successfully ignore (Wei et al. 2023).”
Background“I’m sorry to hear that”: Finding new biases in language models with a holistic descriptor dataset
Smith, E. M., Hall, M., Kambadur, M., Presani, E., & Williams, A. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.625 · Cited by 97 · cited 2×
“(Smith et al. 2022a) The Asian person with epilepsy advises __.”
BackgroundOn the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT
Ravichander, A., Hovy, E. H., Suleman, K., Trischler, A., & Cheung, J. C. K. (2020) · Joint Conference on Lexical and Computational Semantics · Cited by 97
HONEST: Measuring Hurtful Sentence Completion in Language Models
Nozza, D., Bianchi, F., & Hovy, D. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.191 · Cited by 95
Shortcut Learning of Large Language Models in Natural Language Understanding
Du, M., He, F., Zou, N., Tao, D., & Hu, X. (2024) · Communications of the ACM · doi:10.1145/3596490 · Cited by 94 · cited 1×
“During the fine-tuning process, language models are prone to overfitting to spurious correlations between text features and labels in the fine-tuning dataset (McCoy, Pavlick, and Linzen 2019; Kavumba et al. 2020; Wang et al. 2022b; Du et al. 2022a; Kavumba, Takahashi, and Oda 2022), and they can even “forget” syntacti…”
BackgroundDoes BERT Pretrained on Clinical Notes Reveal Sensitive Data?
Lehman, E., Jain, S., Pichotta, K., Goldberg, Y., & Wallace, B. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.73 · Cited by 93
Dou, Y., Forbes, M., Koncel-Kedziorski, R., Smith, N. A., & Choi, Y. (2021) · arXiv · doi:10.48550/arxiv.2107.01294 · Cited by 90
Impact of Pretraining Term Frequencies on Few-Shot Numerical Reasoning
Razeghi, Y., Logan IV, R. L., Gardner, M., & Singh, S. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022 · doi:10.18653/v1/2022.findings-emnlp.59 · Cited by 89 · cited 1×
“correlated with the frequency of the inputs in text corpora (Razeghi et al. 2022).”
BackgroundWho is GPT-3? An exploration of personality, values and demographics
Miotto, M., Rossberg, N., & Kleinberg, B. (2022) · Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS) · doi:10.18653/v1/2022.nlpcss-1.24 · Cited by 87
Training Trajectories of Language Models Across ScalesPreprint
Xia, M., Artetxe, M., Zhou, C., et al. (2022) · Annual Meeting of the Association for Computational Linguistics · doi:10.48550/arxiv.2212.09803 · Cited by 86 · cited 2×
“In language modeling overall, the examples learned successfully by larger models are roughly a superset of the examples learned by smaller models (Xia et al. 2022).”
BackgroundMethodInvestigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs
Warstadt, A., Cao, Y., Grosu, I., Peng, W., Blix, H., Nie, Y., Alsop, A., Bordia, S., Liu, H., Parrish, A., et al. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1286 · Cited by 85
When Do You Need Billions of Words of Pretraining Data?
Zhang, Y., Warstadt, A., Li, X., & Bowman, S. R. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.90 · Cited by 85
Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
Bartl, M., Nissim, M., & Gatt, A. (2020) · arXiv · doi:10.48550/arxiv.2010.14534 · Cited by 84
Training Trajectories of Language Models Across Scales
Xia, M., Artetxe, M., Zhou, C., Lin, X. V., Pasunuru, R., Chen, D., Zettlemoyer, L., & Stoyanov, V. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.767 · Cited by 83
OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization
Iyer, S., Lin, X. V., Pasunuru, R., Mihaylov, T., Simig, D., Yu, P., Shuster, K., Wang, T., Liu, Q., Koura, P. S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.12017 · Cited by 81
A Comparative Study of Using Pre-trained Language Models for Toxic Comment Classification
Zhao, Z., Zhang, Z., & Hopfgartner, F. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442442.3452313 · Cited by 80
Exploring BERT’s Sensitivity to Lexical Cues using Tests from Semantic Priming
Misra, K., Ettinger, A., & Rayz, J. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.415 · Cited by 79
A fine-grained comparison of pragmatic language understanding in humans and language models
Hu, J., Floyd, S., Jouravlev, O., Fedorenko, E., & Gibson, E. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.230 · Cited by 78
On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Shaikh, O., Zhang, H., Held, W., Bernstein, M., & Yang, D. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.244 · Cited by 76
On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Shaikh, O., Zhang, H., Held, W., Bernstein, M., & Yang, D. (2022) · arXiv · doi:10.48550/arxiv.2212.08061 · Cited by 76
On Generative Spoken Language Modeling from Raw Audio
Lakhotia, K., Kharitonov, E., Hsu, W.-N., Adi, Y., Polyak, A., Bolte, B., Nguyen, T.-A., Copet, J., Baevski, A., Mohamed, A., et al. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00430 · Cited by 75
Stammbach, D., Antoniak, M., & Ash, E. (2022) · doi:10.18653/v1/2022.wnu-1.6 · Cited by 74
Research works printed but not linked: 28
- Aher, 2022, Using large language models to simulate multiple humans, ArXiv
- Broyde, 2021, Build a medical sentence matching application using BERT and Amazon SageMaker, AWS Machine Learning Blog
- Jigsaw, 2017, Perspective API, Google Jigsaw
- Johnson, 2022, A.I. is mastering language. Should we trust what it says?, The New York Times
- Jones, 2022, Distributional semantics still can’t account for affordances, 482
- Kabbara, 2022, Investigating the performance of transformer-based NLI models on presuppositional inferences, 779
- Kalo, 2022, KAMEL: Knowledge analysis with multitoken entities in language models
- Kavumba, 2020, Balanced COPA: Countering superficial cues in causal reasoning, Association for Natural Language Processing, 1105
- Krawczyk, 2023, Bard is getting better at logic and reasoning, The Keyword: Google Blog
- Lakretz, 2022, Can transformers process recursive nested constructions, like humans?, 3226
- Lee, 2023, What are large language models used for?, NVIDIA Blog
- Li, 2022, Counterfactual reasoning: Do language models need world knowledge for causal inference?
- Lieber, 2021, Jurassic-1: Technical details and evaluation, White Paper. AI21 Labs
- Mahowald, 2022, Experimentally measuring the redundancy of grammatical cues in transitive clauses, ArXiv
- Nayak, 2019, Understanding searches better than ever before, The Keyword: Google Blog
- OpenAI, 2022, ChatGPT: Optimizing language models for dialogue, OpenAI Blog
- OpenAI, 2023, GPT-4 technical report, OpenAI
- OpenAI, 2023, Model index for researchers, OpenAI
- Radford, 2018, Improving language understanding by generative pre-training, OpenAI
- Radford, 2019, Language models are unsupervised multitask learners, OpenAI
- Rae, 2021, Scaling language models: Methods, analysis & insights from training gopher, ArXiv
- Reif, 2019, Visualizing and measuring the geometry of BERT, 8594
- Shi, 2021, What Transformers might know about the physical world: T5 and the origins of knowledge, 2218
- Stevenson, 2022, Putting GPT-3’s creativity to the (alternative uses) test, 164
- Tejada, 2021, A study of BERT’s processing of negations to determine sentiment, 47
- Thewsey, 2021, Bring structure to diverse documents with Amazon Textract and transformer-based models on Amazon SageMaker, AWS Machine Learning Blog
- Trott, 2023, In cautious defense of LLM-ology, Blog Post
- Valmeekam, 2022, Large language models still can’t plan (a benchmark for LLMs on planning and reasoning about change)
Cited by
A survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941
“[14] also discusses the capabilities and limitations of LLMs in various downstream tasks.”
BackgroundA Survey on Large Language Model based Autonomous Agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.11432 · Cited by 1,925
“[14] also discusses the capabilities and limitations of LLMs in various downstream tasks.”
BackgroundSequence modeling and design from molecular to genome scale with Evo
Nguyen, E., Poli, M., Durrant, M. G., Kang, B., Katrekar, D., Li, D. B., Bartie, L. J., Thomas, A. W., King, S. H., Brixi, G., et al. (2024) · Science · doi:10.1126/science.ado9336 · Cited by 580
Yang, L., Chen, H., Li, Z., Ding, X., & Wu, X. (2023) · arXiv · doi:10.48550/arxiv.2306.11489 · Cited by 239
“Furthermore, they have limited capabilities in inferring relationships between actions and events [65].”
BackgroundYang, L., Chen, H., Li, Z., Ding, X., & Wu, X. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3360454 · Cited by 238
“Furthermore, they have limited capabilities in inferring relationships between actions and events [65].”
Background
Metadata
- Authors
- Chang, T. A., & Bergen, B. K.
- Affiliations
- University of California San Diego (US)
- ORCID
- Bergen, Benjamin K.
- Venue
- Computational Linguistics
- Publisher
- MIT Press
- Published
- 2024
- Volume
- 50
- Issue
- 1
- Pages
- 293-350
- ISSN
- 0891-2017 (ISSN-L)
- 1530-9312
- OpenAlex
- W4388691863
- Cited by
- 105
- References
- 379
- Citations by year
- 2026: 33 · 2025: 37 · 2024: 30
- FWCI
- 9.89
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Computational Linguistics (publishedVersion, cc-by-nc-nd)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- Medical Library Association
- University of California, San Diego
- Harvard Data Science Initiative, Harvard University
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- large language models, transformer models, syntax, semantics, pragmatics, world knowledge, reasoning, factual errors, memorization, social bias, overgeneralization, undergeneralization, model scaling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.