RESEARCH

Can LLMs Introspect? A Reality Check

ArXiv cs.AI · Wed, 27 May 2026 04:00:00 GMT

arXiv:2605.26242v1 Announce Type: new Abstract: Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from human metacognition research, that this conclusion may b

Read original source Discuss with A.S.I.S