Large Language Models (LLMs) frequently generate hallucinated content, posing significant challenges for applications where factuality is crucial. While existing hallucination detection methods typically operate at the sentence level or passage level, we propose FactSelfCheck, a novel zero-resource black-box sampling-based method that enables fine-grained fact-level detection. Our approach represents text as interpretable knowledge graphs consisting of facts in the form of triples, providing clearer insights into content factuality than traditional approaches. Through analyzing factual consistency across multiple LLM responses, we compute fine-grained hallucination scores without requiring external resources or training data. Our evaluation demonstrates that FactSelfCheck performs competitively with leading sentence-level sampling-based methods while providing more detailed and interpretable insights. Most notably, our fact-level approach significantly improves hallucination correction, achieving a 35.5% increase in factual content compared to the baseline, while sentence-level SelfCheckGPT yields only a 10.6% improvement. The granular nature of our detection enables more precise identification and correction of hallucinated content. Additionally, we contribute FavaMultiSamples, a novel dataset that addresses a gap in the field by providing the research community with a second dataset for evaluating sampling-based methods.

翻译：大语言模型（LLMs）经常生成包含幻觉的内容，这对事实准确性至关重要的应用场景构成了重大挑战。现有的幻觉检测方法通常在句子级别或段落级别进行操作，而本文提出FactSelfCheck——一种新颖的零资源黑盒采样方法，能够实现细粒度的事实级检测。我们的方法将文本表示为由三元组形式的事实构成的可解释知识图谱，相比传统方法能够更清晰地揭示内容的事实性。通过分析多个LLM响应之间的事实一致性，我们可以在无需外部资源或训练数据的情况下计算细粒度的幻觉分数。评估结果表明，FactSelfCheck与领先的基于采样的句子级方法相比具有竞争力，同时提供更详细且可解释的洞察。最值得注意的是，我们的事实级方法显著提升了幻觉修正效果，相比基线模型实现了35.5%的事实内容增长，而句子级的SelfCheckGPT仅带来10.6%的改进。我们检测方法的细粒度特性使得能够更精确地识别和修正幻觉内容。此外，我们贡献了FavaMultiSamples数据集，该数据集通过为研究社区提供第二个用于评估基于采样方法的基准数据集，弥补了该领域的空白。