作者位次 #2/7ACL 2026Poster· Natural Language Processing
R e FL : Reflective Feedback Learning for Hallucination Detection of Large Language Models
Cunhang Fan · Jun Zhang · Xue Zhang · Shuai Zhang · Zhao Lv · Jianhua Tao · Zhengqi Wen
摘要
Large Language Models (LLMs) often generate factually incorrect content, known as “hallucinations”, which undermine the reliability and safety of their outputs. Existing hallucination detection methods either depend on external knowledge sources, incurring high computational costs and limiting re...