mlsanityData to 7 Oct 2026

Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs

arXiv 2409.16371 ↗First posted 24 Sep 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper tackles the challenge of building robust and generalizable bias mitigation models for language. Recognizing the limitations of existing datasets, we introduce ANUBIS, a novel dataset with 1507 carefully curated sentence pairs encompassing nine social bias categories. We evaluate state-of-the-art models like T5, utilizing Supervised Fine-Tuning (SFT), Reinforcement Learning (PPO, DPO), and In-Context Learning (ICL) for effective bias mitigation. Our analysis focuses on multi-class social bias reduction, cross-dataset generalizability, and environmental impact of the trained models. ANUBIS and our findings offer valuable resources for building more equitable AI systems and contribute to the development of responsible and unbiased technologies with broad societal impact.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 24 Sep 2024.

Builds on

16 of 35 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  6. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  7. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  8. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  9. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  10. 2022Prompting GPT-3 To Be Reliablecited by 258
  11. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 136
  12. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
4 more
  1. 2019Automatically Neutralizing Subjective Bias in Textcited by 105
  2. 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46
  3. 2020Is Your Classifier Actually Biased? Measuring Fairness under Uncertainty with Bernstein Boundscited by 13
  4. 2024Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIFcited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
  2. 2025An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation
  3. 2025Detection, Classification, and Mitigation of Gender Bias in Large Language Models
  4. 2025BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
  5. 2024BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization
  6. 2024A Multi-LLM Debiasing Framework
  7. 2024BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs
  8. 2025Compositional Bias Control in Large Language Models: Preference Learning Fails, Supervision Succeeds