Research watch · Paper · Oct 2026

Identifying Introspection From the Inside

This paper looks for mechanistic signs that language models can report faithfully on internal signals. It studies a controlled setting where self-report can be checked against known internal states.

Our reading

From: Northeastern University; Eleos AI Research

The authors probe models to identify internal signatures associated with accurate self-report.

They report evidence that some forms of introspection can be detected mechanistically rather than only behaviorally.

The work does not establish that models are conscious, or that self-reports generalize to open-ended real-world settings.

Source: arXiv ↗. This is a summary; the source is the authority.

What it changes

This modestly strengthens the case that some model self-reports track internal signals, but it does not show subjective experience.

How we weigh evidence like this: the evidence levels.