Skip to content
r•Robopsychology
Research AtlasField buildingSalonsConnectTeamAboutSubscribe
MapQuestionsPapersMethodsPeoplev1 · Corrections welcome
Atlas / Digital minds / People

Iulia Comsa

Introspection & Self-report

Google DeepMind

Conceptual criteria for LLM introspection.

Placed by the editor, v1 — corrections welcome.

In the Atlas

  • Keeling Street et al 2024 - Pain and pleasure trade-offs
  • Comsa Shanahan 2025 - Introspection in LLMs

Closest to

  • How well can LLMs introspect

Help improve this map

Know a paper that belongs here, or think something needs correcting?

Suggest a correction ↗Contributions are reviewed before they appear.
Around this researcher
Introspection & Self-reportDoes it make sense to speak of introspection in large language models?Can LLMs make trade-offs involving stipulated pain and pleasure states?How well can LLMs introspect — and how much does "just ask the model" tell us?This researcher

4 connections · Explore on map ↗

Linked from

  • Introspection & Self-report
  • Does it make sense to speak of introspection in large language models?
  • Can LLMs make trade-offs involving stipulated pain and pleasure states?
  • How well can LLMs introspect — and how much does "just ask the model" tell us?

News and updates

Hear when a new map, salon or course opens.

We use your email only for Robopsychology news.

Robopsychology

A field in formation. A map in progress.

Field buildingSalonsConnectField guideTeamAboutAbout the AtlasSuggest a correction
robopsych.org