What AI says about FaithJudge

FaithJudge is a benchmarking suite that evaluates how often large language models introduce hallucinations in retrieval-augmented generation (RAG) tasks, with a focus on reliability and factual accuracy. It assesses models across three tasks—summarization, question answering, and data-to-text generation—and reports hallucination rates. The project provides evaluation data, results, and a leaderboard to compare model performance.