GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence

arXiv:2402.12566v1 Announce Type: cross
Abstract: LLMs can generate factually incorrect statements even when provided access to reference documents. Such errors can be dangerous in high-stakes applications (e.g., document-grounded QA for healthcare or finance). We present GenAudit -- a tool intended to assist fact-checking LLM responses for document-grounded tasks. GenAudit suggests edits to the LLM response by revising or removing claims that are not supported by the reference document, and also presents evidence from the reference for facts that do appear …

abstract applications arxiv cs.cl cs.lg document documents errors evidence fact-checking finance generate healthcare language language model llm llms reference responses tasks tool type