Token-Guard: 通过自检解码实现token级幻觉控制
Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
AI总结：
Token-Guard通过自检解码技术，实现对大型语言模型中token级幻觉的有效控制，提升生成准确性与输出可靠性。
摘要：
大型语言模型（LLMs）常常产生与输入不一致的内容，即幻觉。检索增强生成（RAG）和人类反馈强化学习（RLHF）可以减轻幻觉，但需要资源密集型检索或大规模微调。基于解码的方法更轻量，但缺乏显式的幻觉控制。为此，我们提出了Token-Guard，一种基于自检解码的token级幻觉控制方法。Token-Guard在每个推理步骤中进行内部验证，以在它们传播之前检测到幻觉token。候选片段进一步在潜在空间中进行评估，通过显式的幻觉风险评分进行评估，同时迭代修剪和再生动态纠正检测到的错误。在HALU数据集上的实验表明，Token-Guard显著减少了幻觉并提高了生成准确性，提供了一种可扩展、模块化的可靠LLM输出解决方案。我们的代码已公开可用。
英文摘要：
Large Language Models (LLMs) often hallucinate, generating content inconsistent with the input. Retrieval-Augmented Generation (RAG) and Reinforcement Learning with Human Feedback (RLHF) can mitigate hallucinations but require resource-intensive retrieval or large-scale fine-tuning. Decoding-based methods are lighter yet lack explicit hallucination control. To address this, we present Token-Guard, a token-level hallucination control method based on self-checking decoding. Token-Guard performs internal verification at each reasoning step to detect hallucinated tokens before they propagate. Candidate fragments are further evaluated in a latent space with explicit hallucination risk scoring, while iterative pruning and regeneration dynamically correct detected errors. Experiments on HALU datasets show Token-Guard substantially reduces hallucinations and improves generation accuracy, offering a scalable, modular solution for reliable LLM outputs. Our code is publicly available.
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。
