Ever：通过实时验证与修正缓解大语言模型中的幻觉
Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification
AI总结：
本文提出 Ever 方法，通过实时逐步验证与修正策略在生成过程中即时检测并纠正大语言模型的幻觉，在问答、传记生成和多跳推理等任务上显著提升了事实准确性。
摘要：
大语言模型（LLMs）在生成流畅文本方面展现出卓越能力。然而，它们经常面临生成不准确或幻觉内容的挑战。这一问题在非检索式生成和检索增强生成方法中都很常见，且现有的事后修正方法可能无法解决因“滚雪球”效应而累积的幻觉错误，尤其是在推理任务中。为应对这些挑战，我们提出了一种名为实时验证与修正（Ever）的新方法。Ever 不再等到生成过程结束后才修正幻觉，而是采用实时、逐步的生成与幻觉修正策略，主要目标是在文本生成过程中即时检测并修正幻觉。与基于检索和非检索的基线方法相比，Ever 在生成可信且事实准确的文本方面表现出显著改进，涵盖短篇问答、传记生成和多跳推理等多种任务。
英文摘要：
Large Language Models (LLMs) have demonstrated remarkable proficiency in generating fluent text. However, they often encounter the challenge of generating inaccurate or hallucinated content. This issue is common in both non-retrieval-based generation and retrieval-augmented generation approaches, and existing post-hoc rectification methods may not address the accumulated hallucination errors that may be caused by the "snowballing" issue, especially in reasoning tasks. To tackle these challenges, we introduce a novel approach called Real-time Verification and Rectification (Ever). Instead of waiting until the end of the generation process to rectify hallucinations, Ever employs a real-time, step-wise generation and hallucination rectification strategy. The primary objective is to detect and rectify hallucinations as they occur during the text generation process. When compared to both retrieval-based and non-retrieval-based baselines, Ever demonstrates a significant improvement in generating trustworthy and factually accurate text across a diverse range of tasks, including short-form QA, biography generation, and multi-hop reasoning.
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。
