AI RESEARCH
LLMs Show No Signs Of Individuated Metacognition
arXiv CS.LG
•
ArXi:2605.24299v1 Announce Type: new Confidence-weighted routing, selective abstention, and ensemble weighting all assume that a model's stated confidence is informative about its capability on the question being asked. They presume functional metacognition, the capacity to assess one's own capabilities, without exercising them. Aggregate calibration is well studied, with mixed results, but the underlying structure of elicited confidence is less well understood.