基于不确定表达一致性的黑盒幻觉检测
Black-Box Hallucination Detection via Consistency Under the Uncertain Expression
AI总结：
本文研究LLM幻觉检测问题，通过分析模型在不确定表达下的一致性与事实性的关系，提出一种无需内部状态和外部资源的黑盒检测指标，实验证明其预测事实性的效果优于使用内部知识的基线方法。
摘要：
尽管语言建模在近期取得了巨大进步，但诸如GPT3等大型语言模型（LLMs）因生成非事实性回答（即所谓的“幻觉”问题）而备受诟病。现有的幻觉检测与缓解方法需要外部资源或LLMs的内部状态，例如每个token的输出概率。鉴于LLMs外部API访问受限以及外部资源范围有限，迫切需要建立以黑盒方法为核心的幻觉检测有效途径。在本工作中，我们在研究了LLMs在不确定表达下的行为之后，提出了一种简单的黑盒幻觉检测指标。我们的综合分析表明，当LLMs给出事实性回答时，它们会生成一致的响应；反之，当回答非事实时，则生成不一致的响应。基于该分析，我们提出了一种利用不确定表达的高效黑盒幻觉检测指标。实验表明，与使用LLMs内部知识的基线方法相比，我们的指标更能预测模型回答的事实性。
英文摘要：
Despite the great advancement of Language modeling in recent days, Large Language Models (LLMs) such as GPT3 are notorious for generating non-factual responses, so-called "hallucination" problems. Existing methods for detecting and alleviating this hallucination problem require external resources or the internal state of LLMs, such as the output probability of each token. Given the LLM's restricted external API availability and the limited scope of external resources, there is an urgent demand to establish the Black-Box approach as the cornerstone for effective hallucination detection. In this work, we propose a simple black-box hallucination detection metric after the investigation of the behavior of LLMs under expression of uncertainty. Our comprehensive analysis reveals that LLMs generate consistent responses when they present factual responses while non-consistent responses vice versa. Based on the analysis, we propose an efficient black-box hallucination detection metric with the expression of uncertainty. The experiment demonstrates that our metric is more predictive of the factuality in model responses than baselines that use internal knowledge of LLMs.
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。
