Expert-Guided Extinction of Toxic Tokens for Debiased Generation

TL;DR

This paper introduces EXPOSED, a novel method that effectively reduces social bias in large language models by suppressing toxic tokens without extensive data or complex prompting, improving fairness in generated outputs.

Contribution

EXPOSED is a new expert-guided approach that constructs a debiasing expert from toxic data to suppress harmful tokens in LLM outputs, avoiding extensive fine-tuning or prompt engineering.

Findings

Significantly reduces social bias in LLM outputs

Balances fairness and generation quality effectively

Outperforms existing baselines on fairness benchmarks

Abstract

Large language models (LLMs) can elicit social bias during generations, especially when inference with toxic prompts. Controlling the sensitive attributes in generation encounters challenges in data distribution, generalizability, and efficiency. Specifically, fine-tuning and retrieval demand extensive unbiased corpus, while direct prompting requires meticulously curated instructions for correcting the output in multiple rounds of thoughts but poses challenges on memory and inference latency. In this work, we propose the Expert-Guided Extinction of Toxic Tokens for Debiased Generation (EXPOSED) to eliminate the undesired harmful outputs for LLMs without the aforementioned requirements. EXPOSED constructs a debiasing expert based on the abundant toxic corpus to expose and elicit the potentially dangerous tokens. It then processes the output to the LLMs and constructs a fair distribution by suppressing and attenuating the toxic tokens. EXPOSED is evaluated on fairness benchmarks over three LLM families. Extensive experiments demonstrate that compared with other baselines, the proposed EXPOSED significantly reduces the potential social bias while balancing fairness and generation performance.