LettucePrevent：RAG 中实时预防事实幻觉的新方法
原标题：LettucePrevent - Real-Time Prevention of Factual Hallucinations in RAG
AI 摘要
Hugging Face 博客发布了 LettucePrevent，一种在 RAG 生成循环中集成 token 级检测器以实时抑制事实幻觉的方法。其数字检测器在多个模型上将数字幻觉相对减少超过 60%，但事实检测器仅在 Llama-2 7B 上显著降低幻觉（-26.6%），且运行时开销高达 7 倍。该方法通过自定义 LogitsProcessor 和 Hugging Face custom_generate 模块实现。
正文节选
TL;DR: - LettucePrevent integrates a token-level detector directly into the generation loop with a custom LogitsProcessor , outperforming state-of-the-art hallucination detection models (HDMs) under streaming inference at lower latency. - Our regex-verifiable number detector achieves a >60% relative reduction in numeric hallucinations across all evaluated models with minimal latency overhead, ready to drop into any Hugging Face generate() call. - LettucePrevent reaches a significant reduction (−