A Multi-LLM Debiasing Framework

TL;DR

This paper introduces a novel multi-LLM framework for reducing biases in large language models, utilizing centralized and decentralized approaches, and demonstrates its effectiveness in outperforming existing methods across various social groups.

Contribution

It is the first to propose and evaluate a multi-LLM debiasing framework with centralized and decentralized strategies for bias mitigation.

Findings

Significant bias reduction achieved in LLMs.

Outperforms baseline methods across social groups.

Effective in both centralized and decentralized setups.

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.