pith. sign in

human-interpretable

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 2

years

2026 2

clear filters

representative citing papers

Can LLMs Introspect? A Reality Check

cs.AI · 2026-05-25 · conditional · novelty 6.0

Re-examination of two LLM introspection paradigms with new controls shows models lack privileged access to internal states, performing equivalently with input-only classifiers or near chance on relabeled tasks.

citing papers explorer

Showing 2 of 2 citing papers after filters.