A Primer in BERTology: What We Know About How BERT Works
Open accessThe DOI matches its Crossref record; 213 of the 213 references it cites were found in a registry or an index.
Abstract
Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150 studies of the popular BERT model. We review the current state of knowledge about how BERT works, what kind of information it learns and how it is represented, common modifications to its training objectives and architecture, the overparameterization issue, and approaches to compression. We then outline directions for future research.
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 cited source says what the claim attributes to it.
In the citing paper
“It is advised to apply Bidirectional Encoder Representations from Transformers (BERT) [95,144] to cope with the transferability in cross-domain for cyber grooming detection as it has profoundly bidirectional contextualization and allows the model to gain information from various representations with different positions [146].”
From Online grooming detection: A comprehensive survey of child exploitation in chat logs (2023) · cites this paper as [144]
The cited source says what the claim attributes to it.
In the citing paper
“Contextual models such as BERT 9 can represent each term based on the chat context and lead to a more profound knowledge for semantic analysis [144].”
From Online grooming detection: A comprehensive survey of child exploitation in chat logs (2023) · cites this paper as [144]
The cited source says what the claim attributes to it.
In the citing paper
“Before the emergence of ChatGPT, BERT is a commonly used pre-trained machine learning model for NLP tasks (Wolf et al., 2020), and a ubiquitous baseline in text classification experiments of research in recent years (Rogers et al., 2021).”
From Towards reliable generative AI-driven scaffolding: Reducing hallucinations and enhancing quality in self-regulated learning support (2026) · cites this paper as Rogers et al., 2021
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 · cited 5×
“…search-language-understanding-bert 2 Overview of BERT architecture Fundamentally, BERT is a stack of Transformer encoder layers (Vaswani et al., 2017) which consist of multiple “heads”, i.e., fully-connected neural networks augmented with a self-attention mechanism.”
BackgroundInfluentialBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 5×
“The input representations are computed as fol-Figure 1: BERT fine-tuning (Devlin et al., 2019). lows: BERT first tokenizes the given word into wordpieces (Wu et al., 2016b), and then combines three embedding layers (token, position, and segment) to obtain a fixed-length vector.”
BackgroundMethodInfluentialBERT: 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 5×
“The input representations are computed as fol-Figure 1: BERT fine-tuning (Devlin et al., 2019). lows: BERT first tokenizes the given word into wordpieces (Wu et al., 2016b), and then combines three embedding layers (token, position, and segment) to obtain a fixed-length vector.”
BackgroundMethodInfluentialGlove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 1×
“Unlike the conventional static embeddings (Mikolov et al., 2013a; Pennington et al., 2014), BERT’s representations are contextualized, i.e., every input token is represented by a vector dependent on the particular context of occurrence.”
BackgroundDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
Language 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
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 · cited 11×
“• Removing NSP does not hurt or slightly improves task performance (Liu et al., 2019b; Joshi et al., 2020; Clinchant et al., 2019), especially in cross-lingual setting (Wang et al., 2019b).”
BackgroundMethodResultInfluentialDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“The studies in the knowledge distillation framework (Hinton et al., 2015) use a smaller student-network that is trained to mimic the behavior of a larger teacher-network (BERT-large or BERT-base).”
BackgroundExploring 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 · cited 1×
“(2020) show the same for open-domain QA using T5 model (Raffel et al., 2019).”
BackgroundLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Research works printed but not linked: 76
- Arase Yuki, 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), 5393
- Baevski Alexei, 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), 5360
- He Bai, 2020, arXiv:2004. 14996 [cs]
- Bouraoui Zied, 2019, arXiv:1911.12753 [cs] · arXiv
- Brunner Gino, 2020, International Conference on Learning Representations
- Clark Kevin, 2020, International Conference on Learning Representations
- Conneau Alexis, 2019, arXiv:1911.02116 [cs] · arXiv
- Cui Yiming, 2019, arXiv:1906.08101 [cs] · arXiv
- Da Jeff, 2019, Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, 1
- Devlin Jacob, 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), 4171
- Elazar Yanai, 2020, arXiv:2006. 00995 [cs]
- Ettinger Allyson, 2019, arXiv: 1907.13528 [cs] · arXiv
- Fan Angela, 2019, International Conference on Learning Representations
- Forbes Maxwell, 2019, Proceedings of the 41st Annual Conference of the Cognitive Science Society (CogSci 2019), 7
- Frankle Jonathan, 2019, International Conference on Learning Representations
- Ganesh Prakhar, 2020, arXiv preprint arXiv:2002.11985 · arXiv
- Garg Siddhant, 2020, AAAI
- Gong Linyuan, 2019, International Conference on Machine Learning, 2337
- Gordon Mitchell A., 2020, arXiv preprint arXiv:2002.08307 · arXiv
- Goyal Saurabh, 2020, arXiv preprint arXiv:2001. 08950
- Hao Yaru, 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), 4143
- Hinton Geoffrey, 2014, Deep Learning and Representation Learning Workshop: NIPS 2014
- Hoover Benjamin, 2019, arXiv:1910. 05276 [cs]
- Jain Sarthak, 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), 3543
- Jawahar Ganesh, 2019, 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy
- Jiang Haoming, 2019, arXiv preprint arXiv:1911.03437 · arXiv
- Jiang Zhengbao, 2019, arXiv:1911. 12543 [cs]
- Di Jin, 2020, AAAI 2020
- Kim Taeuk, 2020, ICLR 2020
- Kong Lingpeng, 2019, International Conference on Learning Representations
- Kovaleva Olga, 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), 4356
- Krishna Kalpesh, 2020, ICLR 2020
- Kuznetsov Ilia, 2020, arXiv:2004.14999 [cs] · arXiv
- Lan Zhenzhong, 2020, ICLR
- Li Changmao, 2020, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 5709
- Lin Yongjie, 2019, Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 241
- Liu Nelson F., 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), 1073
- Manning Christopher D., 2020, Proceedings of the National Academy of Sciences, 201907367
- May Chandler, 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), 622
- Thomas McCoy R., 2019, International Conference on Learning Representations
- Michel Paul, 2019, Advances in Neural Information Processing Systems 32 (NIPS 2019)
- Mikolov Tomas, 2013, Advances in Neural Information Processing Systems 26 (NIPS 2013), 3111
- Jiaqi Mu, 2018, International Conference on Learning Representations
- Pimentel Tiago, 2020, arXiv:2004. 03061 [cs]
- Poerner Nina, 2019, arXiv preprint arXiv: 1911.03681 · arXiv
- Raganato Alessandro, 2020, arXiv:2002.10260 [cs] · arXiv
- Richardson Kyle, 2020, AAAI 2020
- Richardson Kyle, 2019, arXiv:1912.13337 [cs] · arXiv
- Roberts Adam, 2020, arXiv preprint arXiv:2002.08910 · arXiv
- Rogers Anna, 2020, AAAI, 11
- Sanh Victor, 2019, 5th Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS 2019
- Serrano Sofia, 2019, arXiv:1906.03731 [cs] · arXiv
- Shen Sheng, 2019, arXiv preprint arXiv:1909. 05840
- Stickland Asa Cooper, 2019, International Conference on Machine Learning, 5986
- Strubell Emma, 2019, ACL 2019
- Sugawara Saku, 2020, AAAI
- Sun Siqi, 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), 4314
- Talmor Alon, 2019, arXiv:1912.13283 [cs] · arXiv
- Tenney Ian, 2019, International Conference on Learning Representations
- Schijndel Marten van, 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), 5831
- Vaswani Ashish, 2017, Advances in Neural Information Processing Systems, 5998
- Vig Jesse, 2019, Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 63
- Vilares David, 2020, Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20)
- Voita Elena, 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), 4387
- Voita Elena, 2020, arXiv:2003.12298 [cs] · arXiv
- Wallace Eric, 2019, arXiv preprint arXiv:1909. 07940
- Warstadt Alex, 2020, Proceedings of the 42nd Annual Virtual Meeting of the Cognitive Science Society
- Warstadt Alex, 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), 2870
- Wolf Thomas, 2020, arXiv:1910.03771 [cs] · arXiv
- Felix Wu, 2019, International Conference on Learning Representations
- Zhiyong Wu, 2020, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 4166
- Yin Pengcheng, 2020, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 8413
- Zadeh Ali Hadi, 2020, arXiv:2005.03842 [cs, stat] · arXiv
- Zhang Zhuosheng, 2020, AAAI 2020
- Zhao Sanqiang, 2019, arXiv preprint arXiv:1909.11687 · arXiv
- Zhou Xuhui, 2020, AAAI 2020
Cited by
Items 401–500 of 1,014
Textual Pre-Trained Models for Gender Identification Across Community Question-Answering Members
Schwarzenberg, P., & Figueroa, A. (2023) · IEEE Access · doi:10.1109/access.2023.3235735 · Cited by 21
“While there is a wide consensus in studies with different tasks, datasets, and methodologies that syntactic information is most prominent in the middle layers [17], there are some disagreements regarding semantic features.”
BackgroundJiang, W., Kim, M., Cheung, C., Kim, H., Thiruvathukal, G. K., & Davis, J. C. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10711-4 · Cited by 30
Less is More: Attention Supervision with Counterfactuals for Text Classification
Choi, S. L., Park, H., Yeo, J., & Hwang, S.-W. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.543 · Cited by 25
“This motivates us to supervise attention for BERT, though understanding of BERT internals, such as (Rogers et al., 2020), is mostly observational at this stage– Intervening with attention would be an interesting future work.”
MethodLeveraging redundancy in attention with Reuse TransformersPreprint
Bhojanapalli, S., Chakrabarti, A., Veit, A., Łukasik, M., Jain, H., Liu, F., Chang, Y.-W., & Kumar, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06821 · Cited by 46
“…has focused on analyzing and interpreting the attention scores computed by trained Transformer models (Serrano & Smith, 2019; Jain & Wallace, 2019; Wiegreffe & Pinter, 2019; Clark et al., 2019; Rogers et al., 2020) to gain insight into how attention is useful for inference in specific applications.”
BackgroundMethodGeneralization in NLI: Ways (Not) To Go Beyond Simple Heuristics
Bhargava, P., Валентинович, Д. А., & Rogers, A. (2021) · IT University Of Copenhagen (IT University of Copenhagen) · doi:10.48550/arxiv.2110.01518 · Cited by 56
“Although there are many reports of syntactic knowledge in pre-trained BERT (Rogers et al., 2020b), Min et al. (2020) suggest that pre-training does not yield a strong inductive bias to use syntax in downstream tasks, and augmentation “nudges” the model towards that.”
BackgroundSelf-citationShen, K., & Kejriwal, M. (2023) · PLoS ONE · doi:10.1371/journal.pone.0295925 · Cited by 17
Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech
Karlapati, S., Abbas, A., Hodari, Z., Moinet, A., Joly, A., Karanasou, P., & Drugman, T. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413696 · Cited by 22
“Since there has been a lot of work showing correlations between the contextual information captured by BERT and the semantics of the sentence [20], we use BERT as a semantic sampler.”
MethodGlobal Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors
Kaster, M., Zhao, W., & Eger, S. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.701 · Cited by 39
Evaluating the construct validity of text embeddings with application to survey questions
Fang, Q., Nguyen, D., & Oberski, D. L. (2022) · EPJ Data Science · doi:10.1140/epjds/s13688-022-00353-7 · Cited by 30
“As for the original BERT models, we follow the advice of [2, 26] to average the word embeddings produced at the last layer of BERT to form sentence-level embeddings.”
BackgroundMethodK-LM: Knowledge Augmenting in Language Models Within the Scholarly Domain
Kumar, V., Recupero, D. R., Helaoui, R., & Riboni, D. (2022) · IEEE Access · doi:10.1109/access.2022.3201542 · Cited by 19
“To address the limitations of domain knowledge gaps in cross-domain knowledge-driven NLP tasks, the work proposed a BERT-based text classification model called BERT4TC [37].”
MethodInfluentialBeyond Digital "Echo Chambers": The Role of Viewpoint Diversity in Political Discussion
Hada, R., Fard, A. E., Shugars, S., Bianchi, F., Rossini, P., Hovy, D., Tromble, R., & Tintarev, N. (2023) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3539597.3570487 · Cited by 21
BERT4Loc: BERT for Location—POI Recommender System
Bashir, S. R., Raza, S., & Mišić, V. B. (2023) · Future Internet · doi:10.3390/fi15060213 · Cited by 17
Categorizing political campaign messages on social media using supervised machine learning
Stromer‐Galley, J., & Rossini, P. (2023) · Journal of Information Technology & Politics · doi:10.1080/19331681.2023.2231436 · Cited by 23
“Unlike other language representation models, BERT is the first truly bidirectional representation model in which contexts around given words are jointly considered while calculating attention in all layers (for further explanation of how BERT works, see Rogers, Kovaleva, & Rumshishky, 2020).”
Supplementing domain knowledge to BERT with semi-structured information of documents
Chen, J., Wei, Z., Wang, J., Wang, R., Gong, C., Zhang, H., & Miao, D. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121054 · Cited by 18
Oliveira, R., Sörensen, K., & Martens, D. (2023) · European Journal of Operational Research · doi:10.1016/j.ejor.2023.08.031 · Cited by 25
Koyama, K., Hashimoto, K., Nagao, C., & Mizuguchi, K. (2023) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2023.1274599 · Cited by 21
“…(Vaswani et al., 2017) and BERT (Devlin et al., 2018) models, known for their impressive results and interpretability (Voita et al., 2019; Rogers et al., 2020; Hao et al., 2021), have demonstrated the advantages of the cross-attention mechanism in source – target multi-input tasks such…”
BackgroundHumans Learn Language from Situated Communicative Interactions. What about Machines?
Beuls, K., & Eecke, P. V. (2024) · Computational Linguistics · doi:10.1162/coli_a_00534 · Cited by 37
“Although the precise nature of this knowledge is still a very active field of investigation, sometimes referred to as “BERTology” (Rogers, Kovaleva, and Rumshisky 2020), it has been convincingly argued that the reasons why large language models struggle so much with logical and pragmatic inferencing…”
Pecher, B., Srba, I., & Bieliková, M. (2024) · ACM Computing Surveys · doi:10.1145/3691339 · Cited by 34
“For a more comprehensive overview of different language model fine-tuning approaches, please refer to [121, 155],”
Soud, M., Nuutinen, W., & Liebel, G. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112406 · Cited by 22
A GA-Based Approach to Fine-Tuning BERT for Hate Speech Detection
Madukwe, K. J., Gao, X., & Xue, B. (2020) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci47803.2020.9308419 · Cited by 19
“Then, the fine-tuning process allows the model to learn which representations are useful for the downstream task at hand and which to ignore [18], [19].”
MethodExploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy
García, M. (2021) · doi:10.18653/v1/2021.acl-long.281 · Cited by 18
“For Portuguese, we have used the model provided by Hartmann et al. (2017), and for Galician we have trained a new model (see Appendix C for details).”
InfluentialExplaining Contextualization in Language Models using Visual Analytics
Sevastjanova, R., Kalouli, A.-L., Beck, C., Schäfer, H., & El‐Assady, M. (2021) · doi:10.18653/v1/2021.acl-long.39 · Cited by 27
“…remains yet unclear as to what extent LMs like BERT capture complex linguistic phenomena and whether different linguistic properties are learned across the different layers of the model’s architecture: the existing evidence is conflicting and in some cases even contradictory (Rogers et al., 2020).”
BackgroundHow to Dissect a Muppet: The Structure of Transformer Embedding Spaces
Mickus, T., Paperno, D., & Constant, M. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00501 · Cited by 34
From critical technical practice to reflexive data science
Hirsbrunner, S. D., Tebbe, M. R., & Müller-Birn, C. (2022) · Convergence The International Journal of Research into New Media Technologies · doi:10.1177/13548565221132243 · Cited by 21
“Activation patterns of self-attention heads can often be identi fi ed with certain linguistic characteristics (Rogers et al., 2020).”
BackgroundNguyen, K. V., Nguyen-Thuan, P., Nguyen, N. D., Nguyen, A. G.-T., & Nguyen, N. L.-T. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01735-z · Cited by 17
“[62] proposed the general term BERTology to collectively refer to BERT and its variants.”
BackgroundMethodDiscovery of Potential Inhibitors of SARS-CoV-2 Main Protease by a Transfer Learning Method
Zhang, H., Liang, B., Sang, X., An, J., & Huang, Z. (2023) · Viruses · doi:10.3390/v15040891 · Cited by 15
Enhancing Code-Switching for Cross-lingual SLU: A Unified View of Semantic and Grammatical Coherence
Zhu, Z., Cheng, X., Huang, Z., Chen, D., & Zou, Y. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.486 · Cited by 15
“…of the code-switched token ˜ h ′ i is the weighted sum of its corresponding h : P (7) Note that we only employ the alignment in lower six layers to better align the representations for switched tokens due to their superior syntax-capturing ability (Jawahar et al., 2019; Rogers et al., 2020).”
MethodA Survey On Neural Word EmbeddingsPreprint
Sezerer, E., & Tekır, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.01804 · Cited by 36
Cassani, G., Bianchi, F., Attanasio, G., Marelli, M., & Günther, F. (2023) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/b45ys · Cited by 23
Finding Neurons in a Haystack: Case Studies with Sparse Probing
Gurnee, W., Nanda, N., Pauly, M., Harvey, K., Troitskii, D., & Bertsimas, D. (2023) · arXiv · doi:10.48550/arxiv.2305.01610 · Cited by 15
“For language models in particular, there exist many probing studies showing the rich linguistic representations learned by models [19, 20, 21], contributing to the broader field of “BERTology” [22].”
BackgroundTikochinski, R., Goldstein, A., Yeshurun, Y., Hasson, U., & Reichart, R. (2023) · Cerebral Cortex · doi:10.1093/cercor/bhad082 · Cited by 14
“It turns out that the word embedding space effectively encodes many aspects of language, such as syntax, semantics, and pragmatics (Rogers et al. 2020).”
BackgroundTrained on 100 million words and still in shape: BERT meets British National Corpus
Samuel, D., Kutuzov, A., Øvrelid, L., & Velldal, E. (2023) · Findings of the Association for Computational Linguistics: EACL 2023 · doi:10.18653/v1/2023.findings-eacl.146 · Cited by 14
Domain adaptation of a SMILES chemical transformer to SELFIES with limited computational resources
Alhmoudi, O. K., Aboushanab, M., Thameem, M., Elkamel, A., & AlHammadi, A. A. (2025) · Scientific Reports · doi:10.1038/s41598-025-05017-w · Cited by 15
Evaluating deep generative models on cognitive tasks: a case study
Tang, Z., & Kejriwal, M. (2023) · Discover Artificial Intelligence · doi:10.1007/s44163-023-00067-3 · Cited by 16
GhostViT: Expediting Vision Transformers via Cheap Operations
Cao, H., Qu, Z., Chen, G., Li, X., Thiele, L., & Knoll, A. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3326795 · Cited by 20
“As shown in [25] and [26], typical positional patterns, e.g., diagonal or vertical, can be easily generated by convolution operations.”
BackgroundParameter-efficient fine-tuning of pre-trained code models for just-in-time defect prediction
Talib, M. W. A., Nassif, A. B., Azzeh, M., Alesh, Y., & Afadar, Y. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09930-5 · Cited by 22
“The motivation is that pre-trained models encompass general knowledge about their tasks in the lower layers, while specific information about down-stream tasks is generated in the upper layers [80–82].”
Yao, Y., Hasan, W. Z. W., Jiao, W., Dong, X., Ramli, H. R., Norsahperi, N. M. H., & Dong, W. (2024) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2024.1426055 · Cited by 16
Holtzman, A., West, P., & Zettlemoyer, L. (2025) · Journal of Social Computing · doi:10.23919/jsc.2025.0009 · Cited by 38
Lepori, M. A., & McCoy, R. T. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.325 · Cited by 30
Heads-up! Unsupervised Constituency Parsing via Self-Attention Heads
Li, B., Kim, T., Amplayo, R. K., & Keller, F. (2020) · Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (AACL-IJCNLP) · doi:10.18653/v1/2020.aacl-main.43 · Cited by 16
BERT Goes Shopping: Comparing Distributional Models for Product Representations
Tagliabue, J., Bianchi, F., & Yu, B. (2021) · Workshop on e-Commerce and NLP (ECNLP) · doi:10.18653/v1/2021.ecnlp-1.1 · Cited by 20
Improving task-agnostic BERT distillation with layer mapping search
Jiao, X., Chang, H., Yin, Y., Shang, L., Jiang, X., Chen, X., Li, L., Wang, F., & Liu, Q. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.050 · Cited by 16
Zeng, C., & Li, S. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/5375334 · Cited by 15
“Popular methods also include analyzing self-attention weights and evaluating the performance of classifiers with different representations as inputs [19].”
BackgroundMethodResultInfluentialRetractedLu, Q., Dou, D., & Nguyen, T. H. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.325 · Cited by 33
“which results in their incompetence on knowledgedriven tasks (Rogers et al., 2020).”
BackgroundAnalyzing BERT’s Knowledge of Hypernymy via Prompting
Hanna, M., & Mareček, D. (2021) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2021.blackboxnlp-1.20 · Cited by 40
Paul, W., Cao, Y., Zhang, M., & Burlina, P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-90874-4_17 · Cited by 23
Liu, D., Greene, D., & Dong, R. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.178 · Cited by 16
“Therefore, considerable work has attempted to understand the role played by the different attention heads (Rogers et al., 2020).”
BackgroundLocal Structure Matters Most: Perturbation Study in NLU
Clouâtre, L., Parthasarathi, P., Zouaq, A., & Chandar, S. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.293 · Cited by 30
“As we are interested in the marginal utility of positional embeddings with relation to NPT Transformers, we report the difference in performance between the model that has access to those embeddings and the model that does not (∆ GLUE Score).”
BackgroundInfluentialInterpretability of BERT Latent Space through Knowledge Graphs
Anelli, V. W., Biancofiore, G. M., Bellis, A., Noia, T. D., & Sciascio, E. D. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557617 · Cited by 19
“Also, they are aware of semantic roles, entity types, and relations derived from linguistic knowledge [19].”
BackgroundDecoding Prompt Syntax: Analysing its Impact on Knowledge Retrieval in Large Language Models
Linzbach, S., Tressel, T., Kallmeyer, L., Dietze, S., & Jabeen, H. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543873.3587655 · Cited by 25
“Since the proposal of transformer-based LLMs which learn representations through Masked Language Modelling (MLM-task) [2], two research felds have emerged: (1) Understanding the knowledge inherent in LLMs [25], and (2) Enhancing the LLMs’ inherent knowledge [33].”
MethodIdentify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks
Bauer, L., & Bansal, M. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.192 · Cited by 16
Yaseen, U., & Langer, S. (2021) · Social Media Mining for Health Research and Applications Workshop and Shared Tasks (SMM4H) · doi:10.18653/v1/2021.smm4h-1.14 · Cited by 16
The Hitchhiker’s Guide to Computational Linguistics in Suicide Prevention
Ophir, Y., Tikochinski, R., Klomek, A. B., & Reichart, R. (2021) · Clinical Psychological Science · doi:10.1177/21677026211022013 · Cited by 23
“These powerful language encoders influenced both the scientific and the industrial communities, enhancing most CL applications (Rogers et al., 2020).”
BackgroundA howling success or a working sea? Testing what BERT knows about metaphors
Pedinotti, P., Palma, E. D., Cerini, L., & Lenci, A. (2021) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2021.blackboxnlp-1.13 · Cited by 30
“The application of this last question to other aspects of language has characterized the field of study known as BERTology (Rogers et al., 2020).”
BackgroundPack Together: Entity and Relation Extraction with Levitated Marker.Preprint
Ye, D., Lin, Y., & Sun, M. (2021) · arXiv (Cornell University) · Cited by 14
Attention Approximates Sparse Distributed MemoryPreprint
Bricken, T., & Pehlevan, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.05498 · Cited by 20
“This probabilistic interpretation could explain evidence showing that Attention heads pay attention to different inputs and why some are redundant post training [38, 39, 10].”
BackgroundInfluentialQuantifying gender bias towards politicians in cross-lingual language models
Stańczak, K., Ray Choudhury, S., Pimentel, T., Cotterell, R., & Augenstein, I. (2023) · PLOS ONE · doi:10.1371/journal.pone.0277640 · Cited by 13
“However, most recent large language models are not trained with language generation in mind – their pre-training consists in predicting masked tokens in already existing sentences (Rogers et al., 2021).”
BackgroundLLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models
Kostikova, A., Wang, Z., Bajri, D., Pütz, O., Paaßen, B., & Eger, S. (2026) · ACM Computing Surveys · doi:10.1145/3801096 · Cited by 38
“We also exclude data prior to 2022, even though interest in limitations of smaller-scale LMs had already been rising since the introduction of models like BERT in 2018 [69, 98].”
Conversational Machine Reading Comprehension for Vietnamese Healthcare Texts
Luu, S. T., Bui, M. N., Nguyen, L. D., Tran, K. V., Nguyen, K. V., & Nguyen, N. L.-T. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-88113-9_44 · Cited by 13
“learning using pre-trained language models [4, 5, 12, 18] to enhance the performance of CMC models on the UIT-ViCoQA corpus.”
MethodDeep Learning with Self-Attention Mechanism for Fake News Detection
Cvitanović, I., & Babac, M. B. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-90087-8_10 · Cited by 15
Classification of Poverty Condition Using Natural Language Processing
Santa, G. M., Escobar-Grisales, D., López-Pabón, F. O., Pérez-Toro, P. A., & Orozco‐Arroyave, J. R. (2022) · Social Indicators Research · doi:10.1007/s11205-022-02883-z · Cited by 18
“Figure adapted from Alammar (2020) fully connected neural network Rogers et al. (2020).”
MethodInfluentialDetecting Spam Reviews on Vietnamese E-Commerce Websites
Dinh, C. V., Luu, S. T., & Nguyen, A. G.-T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-21743-2_48 · Cited by 14
“In the Vietnamese language, there are two kinds of BERTology approaches: multilingual and monolingual models [28,7].”
BackgroundSketchXAI: A First Look at Explainability for Human Sketches
Qu, Z., Gryaditskaya, Y., Li, K., Pang, K., Xiang, T., & Song, Y.-Z. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02234 · Cited by 28
“Early works in text models explainability also started with visualisations [1, 68, 86], moving onto linguistic phenomena [8,39,80], and most recently to attention [20,61,71].”
BackgroundGive Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models
Youssef, P., Koraş, O. A., Li, M., Schlötterer, J., & Seifert, C. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.1043 · Cited by 52
Zhao, E., Qu, N., Wang, Y., & Gao, C. (2024) · Remote Sensing · doi:10.3390/rs16071284 · Cited by 13
“The Transformer model is a widely utilized deep learning architecture in the domain of Natural Language Processing (NLP), introduced by Vaswani et al. [31,32].”
The Fill-Mask Association Test (FMAT): Measuring propositions in natural language.
Bao, H. (2024) · Journal of Personality and Social Psychology · doi:10.1037/pspa0000396 · Cited by 20
Hanić, S., Babac, M. B., Gledec, G., & Horvat, M. (2024) · Computers · doi:10.3390/computers13100248 · Cited by 15
Hasan, M. J., Rahman, F., & Mohammed, N. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105764 · Cited by 16
Natural language processing‐based classification of early Alzheimer's disease from connected speech
Balabin, H., Tamm, B., Spruyt, L., Dusart, N., Kabouche, I., Eycken, E., Statz, K., Meyer, S. D., hamme, H. V., Dupont, P. J., et al. (2025) · Alzheimer s & Dementia · doi:10.1002/alz.14530 · Cited by 21
“13 Consequently, these models eliminate the need to explicitly define and extract such features.”
Large Language Model Based Intelligent Fault Information Retrieval System for New Energy Vehicles
Zhang, H., Zhao, Y., Sun, B., Wu, Y., Fu, Z., & Xiao, X. (2025) · Applied Sciences · doi:10.3390/app15074034 · Cited by 18
Ransomware detection and family classification using fine-tuned BERT and RoBERTa models
Hussain, A., Saadia, A., & Alserhani, F. (2025) · Egyptian Informatics Journal · doi:10.1016/j.eij.2025.100645 · Cited by 24
Xu, Y., Zhang, Y., Deng, X., Lee, S.-Y., & Wang, K. (2025) · Case Studies on Transport Policy · doi:10.1016/j.cstp.2025.101562 · Cited by 13
Evaluating language models for the retrieval and categorization of lexical collocations
Espinosa-Anke, L., Codina, J., & Wanner, L. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.120 · Cited by 24
“They have also been harnessed as supporting resources for knowledge-based NLP (Petroni et al., 2019), as they capture a wealth of linguistic phenomena (Rogers et al., 2020).”
BackgroundCalixto, I., Raganato, A., & Pasini, T. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.286 · Cited by 24
“Motivated by recent studies on pretrained language encoders demonstrating that semantic features are highlighted in higher layers (Raganato and Tiede-mann, 2018; Jawahar et al., 2019; Cui et al., 2020; Rogers et al., 2021), we further train only the last two layers of the MMLM.”
BackgroundChalkidis, I., Fergadiotis, M., Tsarapatsanis, D., Αλέτρας, Ν., Androutsopoulos, I., & Malakasiotis, P. (2021) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.2103.13084 · Cited by 34
“…point of view, the main focus is to demystify a model’s inner workings, for example targeting self-attention mechanisms (Jain and Wallace, 2019; Wiegreffe and Pinter, 2019), and more recently Transformer-based language models (Clark et al., 2019; Kovaleva et al., 2019; Rogers et al., 2020).”
BackgroundDeep Neural Network and Boosting Based Hybrid Quality Ranking for e-Commerce Product Search
Jbene, M., Tigani, S., Saadane, R., & Chehri, A. (2021) · Big Data and Cognitive Computing · doi:10.3390/bdcc5030035 · Cited by 14
Shapley Idioms: Analysing BERT Sentence Embeddings for General Idiom Token Identification
Nedumpozhimana, V., Klubička, F., & Kelleher, J. D. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.813967 · Cited by 16
“…al., 2019) and subject-predicate agreement (van Schijndel et al., 2019); and semantic knowledge, such as semantic roles (Ettinger, 2020), and entity types and relations (Tenney et al., 2019); and we direct the reader to Rogers et al. (2020) for a comprehensive recent overview of this probing work.”
BackgroundUsing Facebook language to predict and describe excessive alcohol use
Jose, R., Matero, M., Sherman, G. T., Curtis, B. L., Giorgi, S., Schwartz, H. A., & Ungar, L. (2022) · Alcoholism Clinical and Experimental Research · doi:10.1111/acer.14807 · Cited by 15
DeLong, K. A., Trott, S., & Marta Kutas, A. (2022) · Behavior Research Methods · doi:10.3758/s13428-022-01869-6 · Cited by 13
“, 2020), as well as the extensive body of literature probing where and what kind of information is encoded in BERT (Rogers et al., 2020; Tenney et al., 2019).”
Sevastjanova, R., Kalouli, A.-L., Beck, C., Hauptmann, H., & El‐Assady, M. (2022) · Computer Graphics Forum · doi:10.1111/cgf.14541 · Cited by 26
Pothina, R., & Ganguli, R. (2023) · Minerals · doi:10.3390/min13060770 · Cited by 15
Soler, A. G., & Apidianaki, M. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.598 · Cited by 32
Understanding Transformers for Bot Detection in TwitterPreprint
García-Silva, A., Berrío, C., & Gómez-Pérez, J. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06182 · Cited by 18
“Since pre-trained language models work very well in practice, researchers are trying to under-1 stand how they work (Rogers et al., 2020).”
BackgroundAutomatic Construction of Evaluation Suites for Natural Language Generation DatasetsPreprint
Mille, S., Dhole, K., Mahamood, S., Perez-Beltrachini, L., Gangal, V., Kale, M., van Miltenburg, E., & Gehrmann, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.09069 · Cited by 31
Towards Explainable Fact CheckingPreprint
Augenstein, I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.10274 · Cited by 17
Transformers Generalize Linearly
Petty, J., & Frank, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.12036 · Cited by 10
“Transformer-based models have also shown considerable success on benchmarks that appear to require the representation of hierarchical abstractions (Rogers et al., 2021; Goldberg, 2019; Warstadt et al., 2019).”
BackgroundAmino acid sequence encodes protein abundance shaped by protein stability at reduced synthesis cost
(2024) · doi:10.1002/pro.5239 · Cited by 12
Personality Trait Detection via Transfer Learning
Alshouha, B., Serrano‐Guerrero, J., Chiclana, F., Romero, F. P., & Olivas, J. Á. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.046711 · Cited by 16
Pramudya, Y. G., & Alamsyah, A. (2023) · International Conference on Information and Communications Technology (ICOIACT) · doi:10.1109/icoiact59844.2023.10455890 · Cited by 12
“BERT and RoBERTa have emerged as state-of-the-art models in numerous NLP areas, including the analysis of text-based data like customer reviews [23].”
BackgroundSekli, G. M. (2024) · Kybernetes · doi:10.1108/k-03-2024-0554 · Cited by 14
Dove, G. O. (2024) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2023.0149 · Cited by 21
“Deciphering the extent to which systems employing these models understand, or fail to understand, semantic content has become something of a cottage industry (e.g. [1,2]).”
Are queries and keys always relevant? A case study on transformer wave functions
Rende, R., & Viteritti, L. L. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ada1a0 · Cited by 16
“The remarkable generalization properties of Transformers in NLP tasks have been associated with the use of attention weights that depend on the input values, thereby capturing powerful inductive biases related to the semantics in natural languages [8, 9].”
Wei, Z., Qu, S., Li, Z., Shi, Q., & Zhang, C. (2025) · Sensors · doi:10.3390/s25072062 · Cited by 13
“They are not very good at capturing long-distance dependencies in character sequences because they are usually trained based on the context of local windows, thus losing some important sequence information [47].”
Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality
Aguilar, G., McCann, B., Niu, T., Rajani, N. F., Keskar, N. S., & Solorio, T. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.141 · Cited by 23
Mediators in Determining what Processing BERT Performs First
Slobodkin, A., Choshen, L., & Abend, O. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.8 · Cited by 13
“, 2020), and especially the behavior of BERT (Devlin et al., 2019; Rogers et al., 2020), perhaps the most widely used of Transformer-based models.”
MethodInfluentialBESKlus : BERT Extractive Summarization with K-Means Clustering in Scientific Paper
Samosir, F. V. P., Toba, H., & Ayub, M. (2022) · Jurnal Teknik Informatika dan Sistem Informasi · doi:10.28932/jutisi.v8i1.4474 · Cited by 16
“In [10] we also consider a more general class of algorithms that update subsets of variables at each iteration.”
BackgroundInfluentialWhat neural networks know about linguistic complexity
Sharoff, S. (2022) · Russian Journal of Linguistics · doi:10.22363/2687-0088-30178 · Cited by 13
CxGBERT: BERT meets Construction Grammar
Madabushi, H. T., Romain, L., Divjak, D., & Milin, P. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.355 · Cited by 84
Introducing Orthogonal Constraint in Structural Probes
Limisiewicz, T., & Mareček, D. (2021) · doi:10.18653/v1/2021.acl-long.36 · Cited by 27
Exploring the Data Efficiency of Cross-Lingual Post-Training in Pretrained Language Models
Lee, C., Yang, K., Whang, T., Park, C., Matteson, A. S., & Lim, H. (2021) · Applied Sciences · doi:10.3390/app11051974 · Cited by 20
“While not being the first, BERT [1] has arguably become the most successful in generating contextualized representations, leading to a new research field termed BERTology with hundreds of publications [20].”
Background
Metadata
- Authors
- Rogers, A., Kovaleva, O., & Rumshisky, A.
- Affiliations
- University of Copenhagen (DK)
- University of Massachusetts Lowell (US)
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2020-12
- Volume
- 8
- Pages
- 842-866
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W3006881356
- Cited by
- 1,552
- References
- 182
- Citations by year
- 2026: 171 · 2025: 249 · 2024: 183 · 2023: 292 · 2022: 237 · 2021: 320 · 2020: 100
- FWCI
- 93.20
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- IT University Of Copenhagen (IT University of Copenhagen) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1844740)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- BERT, transformer models, pre-trained language models, model interpretability, training objectives, model architecture modification, overparameterization, model compression, learned representations
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.