FactCHD: Benchmarking Fact-Conflicting Hallucination Detection
This addresses the issue of unreliable LLM outputs for users in real-world applications, but it is incremental as it focuses on benchmarking and detection rather than solving hallucinations directly.
The paper tackles the problem of fact-conflicting hallucinations in LLMs by introducing FactCHD, a benchmark for detecting such errors, and experiments show current methods have shortcomings in accurately identifying factual errors.
Despite their impressive generative capabilities, LLMs are hindered by fact-conflicting hallucinations in real-world applications. The accurate identification of hallucinations in texts generated by LLMs, especially in complex inferential scenarios, is a relatively unexplored area. To address this gap, we present FactCHD, a dedicated benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. A distinctive element of FactCHD is its integration of fact-based evidence chains, significantly enhancing the depth of evaluating the detectors' explanations. Experiments on different LLMs expose the shortcomings of current approaches in detecting factual errors accurately. Furthermore, we introduce 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 is available at https://github.com/zjunlp/FactCHD.