DHI: 利用多样化幻觉诱导提升大语言模型对比事实性控制
DHI: Leveraging Diverse Hallucination Induction for Enhanced Contrastive Factuality Control in Large Language Models
AI总结：
DHI通过多样化幻觉诱导提升大语言模型对比事实性控制，有效减少幻觉生成。
摘要：
大型语言模型（LLMs）经常产生不准确或虚构的信息，称为
英文摘要：
Large language models (LLMs) frequently produce inaccurate or fabricated information, known as "hallucinations," which compromises their reliability. Existing approaches often train an "Evil LLM" to deliberately generate hallucinations on curated datasets, using these induced hallucinations to guide contrastive decoding against a reliable "positive model" for hallucination mitigation. However, this strategy is limited by the narrow diversity of hallucinations induced, as Evil LLMs trained on specific error types tend to reproduce only these particular patterns, thereby restricting their overall effectiveness. To address these limitations, we propose DHI (Diverse Hallucination Induction), a novel training framework that enables the Evil LLM to generate a broader range of hallucination types without relying on pre-annotated hallucination data. DHI employs a modified loss function that down-weights the generation of specific factually correct tokens, encouraging the Evil LLM to produce diverse hallucinations at targeted positions while maintaining overall factual content. Additionally, we introduce a causal attention masking adaptation to reduce the impact of this penalization on the generation of subsequent tokens. During inference, we apply an adaptive rationality constraint that restricts contrastive decoding to tokens where the positive model exhibits high confidence, thereby avoiding unnecessary penalties on factually correct tokens. Extensive empirical results show that DHI achieves significant performance gains over other contrastive decoding-based approaches across multiple hallucination benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
