作者位次 #2/5ACL 2026Poster· Natural Language Processing
Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
Tomer Ashuach · Shai Gretz · Yoav Katz · Yonatan Belinkov · Liat Ein-Dor
摘要
Humans use introspection to evaluate their understanding through private internal states inaccessible to external observers. We investigate whether large language models possess similar privileged knowledge about answer correctness, information unavailable through external observation. We train c...