Zero-Shot Multi-task Hallucination Detection

arXiv:2403.12244v1 Announce Type: new
Abstract: In recent studies, the extensive utilization of large language models has underscored the importance of robust evaluation methodologies for assessing text generation quality and relevance to specific tasks. This has revealed a prevalent issue known as hallucination, an emergent condition in the model where generated text lacks faithfulness to the source and deviates from the evaluation criteria. In this study, we formally define hallucination and propose a framework for its quantitative detection in a zero-shot …

abstract arxiv cs.cl detection evaluation generated hallucination importance issue language language models large language large language models quality robust specific tasks studies tasks text text generation type zero-shot