FACTOID: FACtual enTailment fOr hallucInation Detection

arXiv:2403.19113v1 Announce Type: new
Abstract: The widespread adoption of Large Language Models (LLMs) has facilitated numerous benefits. However, hallucination is a significant concern. In response, Retrieval Augmented Generation (RAG) has emerged as a highly promising paradigm to improve LLM outputs by grounding them in factual information. RAG relies on textual entailment (TE) or similar methods to check if the text produced by LLMs is supported or contradicted, compared to retrieved documents. This paper argues that conventional TE methods are inadequate …

abstract adoption arxiv benefits cs.ai cs.cl detection hallucination however information language language models large language large language models llm llms paradigm rag retrieval retrieval augmented generation textual them type