Caspar Kaiser, Sean Enderby · 2026 · arXiv
Tests self-reported sentience in small open models and finds no reliable evidence for it.
Author list not yet verified for v1. Title, year and link were checked.
Atlas / Digital minds / Paper
No reliable evidence of self-reported sentience in small large language models
Introspection & Self-reportWelfare
Help improve this map
Know a paper that belongs here, or think something needs correcting?
Suggest a correction ↗Contributions are reviewed before they appear.