Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Projective Methods for Mitigating Gender Bias in Pre-trained Language Models (2403.18803v1)

Published 27 Mar 2024 in cs.CL

Abstract: Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained LLMs. We study to what extent the simplest projective debiasing methods, developed for word embeddings, can help when applied to BERT's internal representations. Projective methods are fast to implement, use a small number of saved parameters, and make no updates to the existing model parameters. We evaluate the efficacy of the methods in reducing both intrinsic bias, as measured by BERT's next sentence prediction task, and in mitigating observed bias in a downstream setting when fine-tuned. To this end, we also provide a critical analysis of a popular gender-bias assessment test for quantifying intrinsic bias, resulting in an enhanced test set and new bias measures. We find that projective methods can be effective at both intrinsic bias and downstream bias mitigation, but that the two outcomes are not necessarily correlated. This finding serves as a warning that intrinsic bias test sets, based either on LLMing tasks or next sentence prediction, should not be the only benchmark in developing a debiased LLM.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023.
  2. Investigating gender bias in BERT. Cogn. Comput., 13(4):1008–1018.
  3. Language (technology) is power: A critical survey of “bias” in NLP. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5454–5476, Online. Association for Computational Linguistics.
  4. Stereotyping Norwegian salmon: An inventory of pitfalls in fairness benchmark datasets. In 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), pages 1004–1015, Online. Association for Computational Linguistics.
  5. Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. In Advances in Neural Information Processing Systems, volume 29, pages 4349–4357. Curran Associates, Inc.
  6. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642, Lisbon, Portugal. Association for Computational Linguistics.
  7. Can NLI models verify QA systems’ predictions? In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3841–3854, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  8. Qian Chen and Wen Wang. 2020. Sequential neural networks for noetic end-to-end response selection. Comput. Speech Lang., 62(C).
  9. Hillary Dawkins. 2021. Marked attribute bias in natural language inference. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4214–4226, Online. Association for Computational Linguistics.
  10. On measuring and mitigating biased inferences of word embeddings. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):7659–7666.
  11. BERT: Pre-training of deep bidirectional transformers for language understanding. In 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), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
  12. Ondřej Dušek and Zdeněk Kasner. 2020. Evaluating semantic accuracy of data-to-text generation with natural language inference. In Proceedings of the 13th International Conference on Natural Language Generation, pages 131–137, Dublin, Ireland. Association for Computational Linguistics.
  13. Ranking generated summaries by correctness: An interesting but challenging application for natural language inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2214–2220, Florence, Italy. Association for Computational Linguistics.
  14. Etienne Fortier-Dubois and Domenic Rosati. 2023. Using contradictions improves question answering systems. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 827–840, Toronto, Canada. Association for Computational Linguistics.
  15. Intrinsic bias metrics do not correlate with application bias. In 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), pages 1926–1940, Online. Association for Computational Linguistics.
  16. On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML’17, page 1321–1330. JMLR.org.
  17. On transferability of bias mitigation effects in language model fine-tuning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3770–3783, Online. Association for Computational Linguistics.
  18. Measuring bias in contextualized word representations. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 166–172, Florence, Italy. Association for Computational Linguistics.
  19. A general framework for implicit and explicit debiasing of distributional word vector spaces. In Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020).
  20. Are chatgpt and gpt-4 general-purpose solvers for financial text analytics? a study on several typical tasks.
  21. Towards debiasing sentence representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5502–5515, Online. Association for Computational Linguistics.
  22. On measuring social biases in sentence encoders. In 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), pages 622–628, Minneapolis, Minnesota. Association for Computational Linguistics.
  23. An empirical survey of the effectiveness of debiasing techniques for pre-trained language models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1878–1898, Dublin, Ireland. Association for Computational Linguistics.
  24. StereoSet: Measuring stereotypical bias in pretrained language models. In 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), pages 5356–5371, Online. Association for Computational Linguistics.
  25. CrowS-pairs: A challenge dataset for measuring social biases in masked language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1953–1967, Online. Association for Computational Linguistics.
  26. Alexandru Niculescu-Mizil and Rich Caruana. 2005. Predicting good probabilities with supervised learning. In Proceedings of the 22nd International Conference on Machine Learning, ICML ’05, page 625–632, New York, NY, USA. Association for Computing Machinery.
  27. Bhavish Pahwa and Bhavika Pahwa. 2023. BpHigh at SemEval-2023 task 7: Can fine-tuned cross-encoders outperform GPT-3.5 in NLI tasks on clinical trial data? In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1936–1944, Toronto, Canada. Association for Computational Linguistics.
  28. Aarthi Paramasivam and S. Jaya Nirmala. 2022. A survey on textual entailment based question answering. Journal of King Saud University - Computer and Information Sciences, 34(10, Part B):9644–9653.
  29. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. ArXiv, abs/1910.01108.
  30. Sakib Shahriar and Kadhim Hayawi. 2023. Let’s have a chat! a conversation with chatgpt: Technology, applications, and limitations. Artificial Intelligence and Applications.
  31. Recent advances in natural language inference: A survey of benchmarks, resources, and approaches. arXiv preprint arXiv:1904.01172.
  32. Mitigating gender bias in natural language processing: Literature review. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1630–1640, Florence, Italy. Association for Computational Linguistics.
  33. Bianca Zadrozny and Charles Elkan. 2001. Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers. In Proceedings of the Eighteenth International Conference on Machine Learning, ICML ’01, page 609–616, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc.
  34. Learning gender-neutral word embeddings. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4847–4853, Brussels, Belgium. Association for Computational Linguistics.
  35. A robustly optimized BERT pre-training approach with post-training. In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 1218–1227, Huhhot, China. Chinese Information Processing Society of China.
  36. Can large language models transform computational social science?
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Hillary Dawkins (16 papers)
  2. Isar Nejadgholi (27 papers)
  3. Daniel Gillis (1 paper)
  4. Judi McCuaig (1 paper)