mlsanityData to 7 Oct 2026

Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One

arXiv 2402.12150 ↗First posted 19 Feb 2024cs.CL cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring alternative perspectives from minority parties, resulting in potential biases. We hypothesize that these fairness-violating behaviors occur because LLMs express their viewpoints using a human personality that represents the majority of training data. In response to this, we validate that prompting LLMs with specific roles can allow LLMs to express diverse viewpoints. Building on this insight and observation, we develop FairThinking, a pipeline designed to automatically generate roles that enable LLMs to articulate diverse perspectives for fair expressions. To evaluate FairThinking, we create a dataset with a thousand items covering three fairness-related topics and conduct experiments on GPT-3.5, GPT-4, Llama2, and Mistral to demonstrate its superior performance.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 29 of its 34 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

29 of 34 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2017Deep reinforcement learning from human preferencescited by 3,846
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  9. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  10. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  11. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  12. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
17 more
  1. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  2. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  3. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  4. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
  5. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 202
  6. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 154
  7. 2020UnQovering Stereotyping Biases via Underspecified Questionscited by 124
  8. 2023A Survey on Fairness in Large Language Modelscited by 91
  9. 2023Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicitycited by 86
  10. 2021Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translationcited by 62
  11. 2023TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Modelscited by 56
  12. 2023Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Modelscited by 54
  13. 2023BiasAsker: Measuring the Bias in Conversational AI Systemcited by 52
  14. 2022Perturbation Augmentation for Fairer NLPcited by 51
  15. 2022Evaluating Psychological Safety of Large Language Modelscited by 26
  16. 2023FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicitycited by 22
  17. 2023Fairness of ChatGPTcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 0; 2026: 1.

9 papers.

  1. 2024Large Language Models for Education: A Survey and Outlookcited by 185
  2. 2024Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMscited by 22
  3. 2024Towards Trustworthy AI: A Review of Ethical and Robust Large Language Modelscited by 21
  4. 2024Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Modelscited by 16
  5. 2024Training Language Models to Win Debates with Self-Play Improves Judge Accuracycited by 16
  6. 2024CausalGraph2LLM: Evaluating LLMs for Causal Queriescited by 12
  7. 2024Defending LVLMs Against Vision Attacks through Partial-Perception Supervisioncited by 7
  8. 2024My Words Imply Your Opinion: Reader Agent-based Propagation Enhancement for Personalized Implicit Emotion Analysiscited by 4
  9. 2026Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communitiescited by 0