Fast and Accurate Factual Inconsistency Detection Over Long Documents

SCALE consists of two crucial components. Large Language Models (LLMs) have shown immense First, it builds on a Natural language inference promise in various applications, but deploying (NLI) based method, integrating a novel them in real-time presents certain challenges chunking mechanism for rapid and accurate online such as hallucinations (Cao et al., 2018; Falke et al., performance in diverse natural language generation 2019; Kryściński et al., 2019; Fabbri et al., 2021a; (NLG) tasks. Second, model explanation is Honovich et al., 2022). Hallucinations, or factual essential for real-time deployment of inconsistency inconsistencies generated by a model relative to detection systems, facilitating swift human inspection a source document, can mislead the user and undermine to determine model configurations. We show trust in LLMs. Thus, detecting factual that our chunking mechanism improves calibration inconsistency in LLM generations is crucial for scores and enables the use of a binary search tree the future of LLMs, especially with the growing algorithm for rapidly locating relevant source text popularity of platforms like ChatGPT.