Halu-NLP at SemEval-2024 Task 6: MetaCheckGPT - A Multi-task Hallucination Detection using LLM uncertainty and meta-models
Rahul Mehta, Andrew Hoblitzell, Jack O’keefe, Hyeju Jang, Vasudeva Varma · 2024
Hallucinations in large language models (LLMs) have recently become a significant problem.A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes (Mickus et al., 2024).This paper describes our winning solution ranked 1st and 2nd in the 2 sub-tasks of model agnostic and model aware tracks respectively.We propose a metaregressor framework of LLMs for model evaluation and integration that achieves the highest scores on the leader board.We also experiment with various transformer based models and black box methods like ChatGPT, Vectara, and others.In addition, we perform an error analysis comparing GPT4 against our best model which shows the limitations of the former.