Year: 2026
Type: conference-paper
Abstract: 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 blackbox sampling-based method that enables finegrained fact-level detection.Our approach represents long-form 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 samplingbased 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 FavaMulti-Samples, a novel dataset that addresses a gap in the field by providing the research community with a second dataset for evaluating samplingbased methods.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G3361401150, G4914437490, G6476165626
OpenAlex ID: W7140104327