A Multi-LLM Debiasing Framework

ACL ARR 2024 December Submission367 Authors

Abstract: Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Despite significant advancements in bias mitigation techniques using data augmentation, zero-shot prompting, and model fine-tuning, biases continuously persist, including subtle biases that may elude human detection. Recent research has shown a growing interest in multi-LLM approaches, which have been demonstrated to be effective in improving the quality of reasoning and factuality in LLMs. Building on this approach, we propose a novel multi-LLM debiasing framework aimed at reducing bias in LLMs. Our work is the first to introduce and evaluate two distinct approaches within this framework for debiasing LLMs: a centralized method, where the conversation is facilitated by a single central LLM, and a decentralized method, where all models communicate directly. Our findings reveal that our multi-LLM framework significantly reduces bias in LLMs, outperforming the baseline method across several social groups.

Paper Type: Long

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: Ethics, Bias, and Fairness, Computational Social Science and Cultural Analytics, Generation

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data analysis

Languages Studied: English

Submission Number: 367