Me, Myself, and $Ο€$ : Evaluating and Explaining LLM Introspection

March 17, 2026 Β· Grace Period Β· πŸ› ICLR 2026 Workshop

⏳ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Atharv Naphade, Samarth Bhargav, Sean Lim, Mcnair Shah arXiv ID 2603.20276 Category cs.AI: Artificial Intelligence Citations 0 Venue ICLR 2026 Workshop
Abstract
A hallmark of human intelligence is Introspection-the ability to assess and reason about one's own cognitive processes. Introspection has emerged as a promising but contested capability in large language models (LLMs). However, current evaluations often fail to distinguish genuine meta-cognition from the mere application of general world knowledge or text-based self-simulation. In this work, we propose a principled taxonomy that formalizes introspection as the latent computation of specific operators over a model's policy and parameters. To isolate the components of generalized introspection, we present Introspect-Bench, a multifaceted evaluation suite designed for rigorous capability testing. Our results show that frontier models exhibit privileged access to their own policies, outperforming peer models in predicting their own behavior. Furthermore, we provide causal, mechanistic evidence explaining both how LLMs learn to introspect without explicit training, and how the mechanism of introspection emerges via attention diffusion.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence