Deciphering Stereotypes in Pre-Trained Language Models
Open accessAbstract
Weicheng Ma, Henry Scheible, Brian Wang, Goutham Veeramachaneni, Pratim Chowdhary, Alan Sun, Andrew Koulogeorge, Lili Wang, Diyi Yang, Soroush Vosoughi. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
If M-LLMs are trained on patient data that contain biases related to gender, ethnicity, socioeconomic status, or geographic location, they may inadvertently cause biases in their predictions or recommendations.
“If M-LLMs are trained on patient data that contain biases related to gender, ethnicity, socioeconomic status, or geographic location, they may inadvertently cause biases in their predictions or recommendations [175,178,179].”
From Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook. (2024) · cites this paper as [179]
The Introduction says stereotypes can be inadvertently encoded in pre-trained language models and propagated to downstream applications. Section 7 also suggests that differences in pre-training corpora may contribute to differences in models’ stereotypes. The paper does not examine medical LLMs trained on patient data or establish bias in clinical predictions or recommendations. (LLM, conf=0.83)
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.
Cites
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 48,293 · see citing works
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 · see citing works
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,695 · see citing works
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623 · see citing works
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 · see citing works
Measuring nominal scale agreement among many raters.
Fleiss, J. L. (1971) · Psychological Bulletin · doi:10.1037/h0031619 · Cited by 8,733 · see citing works
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222 · see citing works
HuggingFace's 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. (2019) · arXiv · doi:10.48550/arxiv.1910.03771 · Cited by 3,347 · see citing works
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 · see citing works
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441 · see citing works
Gender bias in coreference resolution: Evaluation and debiasing methods
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (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/n18-2003 · Cited by 684 · see citing works
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 · see citing works
Polynomial calculation of the Shapley value based on sampling
Castro, J., Gómez, D., & Tejada, J. (2009) · Computers & Operations Research · doi:10.1016/j.cor.2008.04.004 · Cited by 601 · see citing works
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 · see citing works
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 · see citing works
Detecting racial bias in algorithms and machine learning
Lee, N. T. (2018) · Journal of Information Communication and Ethics in Society · doi:10.1108/jices-06-2018-0056 · Cited by 263 · see citing works
Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets
Blodgett, S. L., Lopez, G., Olteanu, A., Sim, R., & Wallach, H. (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.81 · Cited by 147 · cited 1× · see citing works
“We pursued this approach because existing stereotype examination datasets often oversimplify the task and have known quality concerns, as indicated by Blodgett et al. (2021).”
BackgroundImplicit stereotypes and the predictive brain: cognition and culture in “biased” person perception
Hinton, P. R. (2017) · Humanities and Social Sciences Communications · doi:10.1057/palcomms.2017.86 · Cited by 96 · see citing works
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 · see citing works
On Measures of Biases and Harms in NLP
Dev, S., Sheng, E., Zhao, J., Amstutz, A., Sun, J., Hou, Y., Sanseverino, M., Kim, J., Nishi, A., Peng, N., et al. (2022) · AACL/IJCNLP · doi:10.18653/v1/2022.findings-aacl.24 · Cited by 49 · see citing works
The MultiBERTs: BERT Reproductions for Robustness Analysis
Sellam, T., Yadlowsky, S., Wei, J., Saphra, N., D'Amour, A., Linzen, T., Bastings, J., Turc, I., Eisenstein, J., Das, D., et al. (2021) · arXiv · doi:10.48550/arxiv.2106.16163 · Cited by 37 · see citing works
On Attention Redundancy: A Comprehensive Study
Bian, Y., Huang, J., Cai, X., Yuan, J., & Church, K. (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.72 · Cited by 36 · see citing works
Roles and Utilization of Attention Heads in Transformer-based Neural Language Models
Jo, J.-Y., & Myaeng, S.-H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.311 · Cited by 33 · see citing works
Attention Flows are Shapley Value Explanations
Ethayarajh, K., & Jurafsky, D. (2021) · doi:10.18653/v1/2021.acl-short.8 · Cited by 24 · see citing works
Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models
Cao, Y., Sotnikova, A., Daumé, H., Rudinger, R., & Zou, L. X. (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.92 · Cited by 24 · see citing works
Choenni, R., Shutova, E., & van Rooij, R. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.111 · Cited by 14 · see citing works
Hutchison, J., & Martin, D. S. (2015) · Evolutionary psychology · doi:10.1007/978-3-319-12697-5_23 · Cited by 8 · see citing works
Flagged first, then by citations
Research works printed but not linked: 3
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901.
- Sergiu Hart. 1989. Shapley value. In Game theory, pages 210-216. Springer.
- Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30, pages 4765-4774.
Cited by
Sorted by citations
Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook.
AlSaad, R., Abd-alrazaq, A., Boughorbel, S., Ahmed, A., Renault, M.-A., Damseh, R., & Sheikh, J. (2024) · Journal of medical Internet research · doi:10.2196/59505 · Cited by 349 · see citing works
“If M-LLMs are trained on patient data that contain biases related to gender, ethnicity, socioeconomic status, or geographic location, they may inadvertently cause biases in their predictions or recommendations [175,178,179].”
Sankar, B. S., Gilliland, D., Rincon, J., Hermjakob, H., Yan, Y., Adam, I., Lemaster, G., Wang, D., Watson, K., Bui, A., et al. (2024) · Bioengineering · doi:10.3390/bioengineering11100984 · Cited by 26 · see citing works
- Authors
- Ma, W., Scheible, H., Wang, B., Veeramachaneni, G., Chowdhary, P., Sun, A., Koulogeorge, A., Wang, L., Yang, D., & Vosoughi, S.
- Affiliations
- Stanford University (US)
- Dartmouth College (US)
- Venue
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Published
- 2023
- Pages
- 11328-11345
- OpenAlex
- W4389524012
- Cited by
- 8
- References
- 27
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 6
- FWCI
- 2.00
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- Topics
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Keywords
- stereotypes, pre-trained language models, bias in language models, natural language processing
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
