Large Language Models (LLMs), such as ChatGPT/GPT-4, have garnered widespread attention owing to their myriad of practical applications, yet their adoption has been constrained by issues of fact-conflicting hallucinations across web platforms. The assessment of factuality in text, produced by LLMs, remains inadequately explored, extending not only to the judgment of vanilla facts but also encompassing the evaluation of factual errors emerging in complex inferential tasks like multi-hop, and etc. In response, we introduce FactCHD, a fact-conflicting hallucination detection benchmark meticulously designed for LLMs. Functioning as a pivotal tool in evaluating factuality within "Query-Respons" contexts, our benchmark assimilates a large-scale dataset, encapsulating a broad spectrum of factuality patterns, such as vanilla, multi-hops, comparison, and set-operation patterns. A distinctive feature of our benchmark is its incorporation of fact-based chains of evidence, thereby facilitating comprehensive and conducive factual reasoning throughout the assessment process. We evaluate multiple LLMs, demonstrating the effectiveness of the benchmark and current methods fall short of faithfully detecting factual errors. Furthermore, we present TRUTH-TRIANGULATOR that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2, aiming to yield more credible detection through the amalgamation of predictive results and evidence. The benchmark dataset and source code will be made available in https://github.com/zjunlp/FactCHD.

翻译：暂无翻译