作者位次 #2/11ACL 2026Findings· Findings of ACL
F aith L ens: Detecting and Explaining Faithfulness Hallucination
Shuzheng Si · Qingyi Wang · Haozhe Zhao · Yuzhuo Bai · Guanqiao Chen · Kangyang Luo · Gang Chen · Fanchao Qi · Minjia Zhang · Baobao Chang · Maosong Sun
摘要
Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retrieval-augmented generation and summarization. In this paper, we introduce FaithLens, a cost-efficient and effective faithfulness hallucination detecti...