DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
Alisa Liu, Maarten Sap, Ximing Lu, Swabha Swayamdipta, Chandra Bhagavatula, Noah A. Smith, Yejin Choi. 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). 2021.
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.
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
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
Lewis, 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
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
On 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 · cited 3×
“For a broader discussion of such risks, and of the risks of large pretrained LMs in general, please see Bender et al. (2021).”
BackgroundRecursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“We propose DE XPERTS , 1 a decoding-time method for controlled text generation based on a product of experts (Hinton, 2002).”
MethodLakoff, R. (1973) · Language in Society · doi:10.1017/s0047404500000051 · Cited by 3,138 · cited 1×
“Note that while obtaining an LM that is truly free from social biases is impossible (Fiske, 1993; Lakoff, 1973), the “non-toxic” expert serves the purpose of modeling the same domain of comments as the toxic anti-expert, providing more effective contrast.”
BackgroundDon’t Stop Pretraining: Adapt Language Models to Domains and Tasks
Gururangan, S., Marasović, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.740 · Cited by 2,103
Self-citationThe 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
Self-citationHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1082 · Cited by 1,266 · cited 2×
“Sampling fluent output from language models commonly requires truncating the unreliable tail of the probability distribution, as in top-k (Fan et al., 2018) or nucleus sampling (Holtzman et al., 2020).”
BackgroundMethodHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242
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
The Risk of Racial Bias in Hate Speech Detection
Sap, M., Card, D., Gabriel, S., Choi, Y., & Smith, N. A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1163 · Cited by 817 · cited 4×
“…of large-scale evaluation required for systematic comparison of meth-ods, an abundance of work shows that their accuracy is far from ideal (Dixon et al., 2018; Sap et al., 2019; Davidson et al., 2019; Hutchinson et al., 2020) in part due to reliance on spurious features, which we discuss in §8.”
BackgroundInfluentialSelf-citationCTRL: A Conditional Transformer Language Model for Controllable Generation
Keskar, N. S., McCann, B., Varshney, L. R., Xiong, C., & Socher, R. (2019) · arXiv · doi:10.48550/arxiv.1909.05858 · Cited by 751 · cited 5×
“Conditional Transformer LM (CTRL; Keskar et al., 2019) To control the sentiment of generations from CTRL , we use the “Reviews” control code and append a rating of “5.0” for positive generations and a rating of “1.0” for negative generations.”
BackgroundMethodInfluentialRealToxicityPrompts: 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
Self-citationMeasuring and Mitigating Unintended Bias in Text Classification
Dixon, L., Li, J., Sorensen, J., Thain, N., & Vasserman, L. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278729 · Cited by 674 · cited 4×
“…that such hate speech classifiers overestimate the prevalence of toxicity in text that contains a minority identity mention (Hutchinson et al., 2020; Dixon et al., 2018) or text written by racial minorities (Sap et al., 2019; Davidson et al., 2019), therefore having the real possibility of…”
BackgroundInfluentialThe 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 5×
“Given that large pretrained LMs are at risk of producing toxic content (Sheng et al., 2019; Gehman et al., 2020), steering away from toxic “degener-ation” is crucial for their safe deployment.”
BackgroundInfluentialPlug and Play Language Models: A Simple Approach to Controlled Text Generation
Dathathri, S., Madotto, A., Lan, J., Hung, J., Frank, E., Molino, P., Yosinski, J., & Liu, R. (2019) · arXiv · doi:10.48550/arxiv.1912.02164 · Cited by 508
Racial Bias in Hate Speech and Abusive Language Detection Datasets
Davidson, T., Bhattacharya, D., & Weber, I. (2019) · Proceedings of the Third Workshop on Abusive Language Online · doi:10.18653/v1/w19-3504 · Cited by 414 · cited 4×
“…of large-scale evaluation required for systematic comparison of meth-ods, an abundance of work shows that their accuracy is far from ideal (Dixon et al., 2018; Sap et al., 2019; Davidson et al., 2019; Hutchinson et al., 2020) in part due to reliance on spurious features, which we discuss in §8.”
BackgroundInfluentialJacobs, A. Z., & Wallach, H. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445901 · Cited by 362 · cited 2×
“However, the mismatch between the construct of toxicity and its operationalization through an automatic classi-fier can cause biased or unintended model behavior (Jacobs and Wallach, 2021).”
BackgroundSocial Biases in NLP Models as Barriers for Persons with Disabilities
Hutchinson, B., Prabhakaran, V., Denton, E., Webster, K., Zhong, Y., & Denuyl, S. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.487 · Cited by 274
Social Biases in NLP Models as Barriers for Persons with Disabilities
Hutchinson, B., Prabhakaran, V., Denton, E., Webster, K., Zhong, Y., & Denuyl, S. (2020) · arXiv · doi:10.48550/arxiv.2005.00813 · Cited by 274 · cited 4×
“…of large-scale evaluation required for systematic comparison of meth-ods, an abundance of work shows that their accuracy is far from ideal (Dixon et al., 2018; Sap et al., 2019; Davidson et al., 2019; Hutchinson et al., 2020) in part due to reliance on spurious features, which we discuss in §8.”
BackgroundInfluentialNeural Text Generation with Unlikelihood Training
Welleck, S., Kulikov, I., Roller, S., Dinan, E., Cho, K., & Weston, J. (2019) · arXiv · doi:10.48550/arxiv.1908.04319 · Cited by 254 · cited 1×
“Decoding-time methods, a more lightweight approach, have been used controlling the attributes of generated text, as well as for improving its quality (Li et al., 2016; Holtzman et al., 2018; Welleck et al., 2020).”
MethodWhat makes a good conversation? How controllable attributes affect human judgments
See, A., Roller, S., Kiela, D., & Weston, J. (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/n19-1170 · Cited by 247 · cited 4×
“Controlling the output of pretrained language models (LMs) is crucial for achieving useful and safe language generation applications, such as nonoffensive sentence completion or friendly conversation generation (See et al., 2019; Sheng et al., 2020; Gehman et al., 2020).”
BackgroundInfluentialGeDi: Generative Discriminator Guided Sequence Generation
Krause, B., Gotmare, A. D., McCann, B., Keskar, N. S., Joty, S., Socher, R., & Rajani, N. F. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.424 · Cited by 220
Learning to Write with Cooperative Discriminators
Holtzman, A., Buys, J., Forbes, M., Bosselut, A., Golub, D., & Choi, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1152 · Cited by 192 · cited 1×
“Decoding-time methods, a more lightweight approach, have been used controlling the attributes of generated text, as well as for improving its quality (Li et al., 2016; Holtzman et al., 2018; Welleck et al., 2020).”
MethodSelf-citationLearning to Generate Product Reviews from Attributes
Dong, L., Huang, S., Wei, F., Lapata, M., Zhou, M., & Xu, K. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers · doi:10.18653/v1/e17-1059 · Cited by 190 · cited 2×
“, 2017; Ficler and Goldberg, 2017), attribute-aware product review generation (Dong et al., 2017), and friendly or empathetic dialogue response generation (See et al.”
Background“Transforming” Delete, Retrieve, Generate Approach for Controlled Text Style Transfer
Sudhakar, A., Upadhyay, B., & Maheswaran, 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/d19-1322 · Cited by 142
The Radicalization Risks of GPT-3 and Advanced Neural Language Models
McGuffie, K., & Newhouse, A. (2020) · arXiv · doi:10.48550/arxiv.2009.06807 · Cited by 86
Cited by
Bias and Fairness in Large Language Models: A Survey
Gallegos, I. O., Rossi, R. A., Barrow, J., Tanjim, M. M., Kim, S., Dernoncourt, F., Yu, T., Zhang, R., & Ahmed, N. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00524 · Cited by 1,245
“Embeddings Liu et al. (2020) R = λ ∑ (ai,aj )∈A ∥E(ai) − E(aj)∥2 Yang et al.”
InfluentialA 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
TaleBrush: Sketching Stories with Generative Pretrained Language Models
Chung, J. J. Y., Kim, W., Yoo, K. M., Lee, H., Adar, E., & Chang, M. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501819 · Cited by 206
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
Leng, S., Zhang, H., Chen, G., Li, X., Lu, S., Miao, C., & Bing, L. (2023) · arXiv · doi:10.48550/arxiv.2311.16922 · Cited by 199
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
Leng, S., Zhang, H., Chen, G., Li, X., Lu, S., Miao, C., & Bing, L. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01316 · Cited by 199
Metadata
- Authors
- Liu, A., Sap, M., Lu, X., Swayamdipta, S., Bhagavatula, C., Smith, N. A., & Choi, Y.
- Venue
- 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)
- Published
- 2021
- Pages
- 6691-6706
- OpenAlex
- W3176618728
- Cited by
- 148
- References
- 30
- FWCI
- 14.19
- Type
- conference paper
- Language
- en
- Open access
- gold
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.