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

arXiv: https://arxiv.org/abs/2402.12150 · HTML: https://mlsanity.com/paper/2402.12150/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 29 of 29)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [UnQovering Stereotyping Biases via Underspecified Questions](https://mlsanity.com/paper/2010.02428/) (2020)
- [A Survey on Fairness in Large Language Models](https://mlsanity.com/paper/2308.10149/) (2023)
- [Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity](https://mlsanity.com/paper/2301.12867/) (2023)
- [Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation](https://mlsanity.com/paper/2109.03858/) (2021)
- [TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models](https://mlsanity.com/paper/2306.11507/) (2023)
- [Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models](https://mlsanity.com/paper/2307.16180/) (2023)
- [BiasAsker: Measuring the Bias in Conversational AI System](https://mlsanity.com/paper/2305.12434/) (2023)
- [Perturbation Augmentation for Fairer NLP](https://mlsanity.com/paper/2205.12586/) (2022)
- [Evaluating Psychological Safety of Large Language Models](https://mlsanity.com/paper/2212.10529/) (2022)
- [FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity](https://mlsanity.com/paper/2311.18580/) (2023)
- [Fairness of ChatGPT](https://mlsanity.com/paper/2305.18569/) (2023)

## Built on by (most cited first, 11 of 11)

- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs](https://mlsanity.com/paper/2404.10160/) (2024)
- [Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models](https://mlsanity.com/paper/2407.13934/) (2024)
- [Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models](https://mlsanity.com/paper/2405.16631/) (2024)
- [Training Language Models to Win Debates with Self-Play Improves Judge Accuracy](https://mlsanity.com/paper/2409.16636/) (2024)
- [CausalGraph2LLM: Evaluating LLMs for Causal Queries](https://mlsanity.com/paper/2410.15939/) (2024)
- [Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks](https://mlsanity.com/paper/2408.15207/) (2024)
- [Defending LVLMs Against Vision Attacks through Partial-Perception Supervision](https://mlsanity.com/paper/2412.12722/) (2024)
- [My Words Imply Your Opinion: Reader Agent-based Propagation Enhancement for Personalized Implicit Emotion Analysis](https://mlsanity.com/paper/2412.07367/) (2024)
- [Reflections and New Directions for Human-Centered Large Language Models](https://mlsanity.com/paper/2605.06901/) (2026)
- [Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities](https://mlsanity.com/paper/2606.13397/) (2026)

## 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.