Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
This addresses the issue of hallucinations in LLMs for users requiring factual text generation, representing a novel method for a known bottleneck.
The paper tackled the problem of hallucinations in large language models during generation by proposing Active Layer-Contrastive Decoding, which actively decides when to apply contrasting layers, resulting in surpassing state-of-the-art methods across five benchmarks.
Recent decoding methods improve the factuality of large language models (LLMs) by refining how the next token is selected during generation. These methods typically operate at the token level, leveraging internal representations to suppress superficial patterns. Nevertheless, LLMs remain prone to hallucinations, especially over longer contexts. In this paper, we propose Active Layer-Contrastive Decoding (ActLCD), a novel decoding strategy that actively decides when to apply contrasting layers during generation. By casting decoding as a sequential decision-making problem, ActLCD employs a reinforcement learning policy guided by a reward-aware classifier to optimize factuality beyond the token level. Our experiments demonstrate that ActLCD surpasses state-of-the-art methods across five benchmarks, showcasing its effectiveness in mitigating hallucinations in diverse generation scenarios.