细粒度细化：用于缓解对话幻觉的迭代细化
Fine-Refine: Iterative Fine-grained Refinement for Mitigating Dialogue Hallucination
AI总结：
Fine-Refine通过细粒度细化框架提升对话系统事实准确性，实现7.63分的提升，同时牺牲少量对话质量。
摘要：
当前大型语言模型（LLMs）在对话系统中表现出幻觉倾向，这会负面影响对话系统。此类幻觉会产生事实性错误的响应，可能误导用户并损害系统信任。现有的对话系统细化方法通常在响应层面操作，忽略了单个响应可能包含多个可验证或不可验证的事实。为解决这一缺口，我们提出了Fine-Refine，一种细粒度细化框架，将响应分解为原子单元，利用外部知识验证每个单元，通过困惑度评估流畅性，并迭代修正细粒度错误。我们评估了HybriDialogue和OpendialKG数据集在事实准确性（事实得分）和覆盖度（不足信息比例）方面的事实性，并实验表明，Fine-Refine显著提高了事实性，实现了对话事实得分提升高达7.63分，仅以对话质量稍有折损为代价。
英文摘要：
The tendency for hallucination in current large language models (LLMs) negatively impacts dialogue systems. Such hallucinations produce factually incorrect responses that may mislead users and undermine system trust. Existing refinement methods for dialogue systems typically operate at the response level, overlooking the fact that a single response may contain multiple verifiable or unverifiable facts. To address this gap, we propose Fine-Refine, a fine-grained refinement framework that decomposes responses into atomic units, verifies each unit using external knowledge, assesses fluency via perplexity, and iteratively corrects granular errors. We evaluate factuality across the HybriDialogue and OpendialKG datasets in terms of factual accuracy (fact score) and coverage (Not Enough Information Proportion), and experiments show that Fine-Refine substantially improves factuality, achieving up to a 7.63-point gain in dialogue fact score, with a small trade-off in dialogue quality.
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。
