Latent Introspection: Models Can Detect Prior Concept Injections

arXiv:2602.20031 · cs.AI, cs.LG · Submitted 2026-02-23 · Read on arXiv

cs.AI, cs.LG

Submitted: 2026-02-23

Updated: 2026-11-07

Comments: 28 pages, 17 figures. Submitted to ICML 2026. Workshop version submitted to ICLR 2026 Workshop on Latent and Implicit Thinking

Code: https://github.com/acsresearch/latent-introspection-code

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers