MetaCheckGPT -- A Multi-task Hallucination Detection Using LLM Uncertainty and Meta-models

arXiv:2404.06948v1 Announce Type: new
Abstract: This paper presents our winning solution for the SemEval-2024 Task 6 competition. We propose a meta-regressor framework of large language models (LLMs) for model evaluation and integration that achieves the highest scores on the leader board. Our approach leverages uncertainty signals present in a diverse basket of LLMs to detect hallucinations more robustly.

abstract arxiv board competition cs.ai cs.cl detection evaluation framework hallucination integration language language models large language large language models leader llm llms meta paper solution type uncertainty