作者位次 #7/9ACL 2026Findings· Findings of ACL
PROBE : PRO cess-Based BE nchmark for Hallucination Detection
Yu Zhang · Peter Belcak · Shizhe Diao · Yonggan Fu · Shaona Ghosh · Morteza Mardani · Eileen Margaret Peters Long · Bei Yu · Pavlo Molchanov
摘要
Hallucination detection remains a significant challenge for large language models. Existing agentic applications rely on LLMs to self-assess the factuality of their outputs using single-step “LLM-as-a-judge” prompts. However, even when equipped with ground truth information, current LLMs still fa...