New arXiv paper: current evidence insufficient to show LLMs can introspect
tallinzen · x · 2026-10-02
The paper "Can LLMs Introspect? A Reality Check" (Singh, Linzen, Ravfogel; to be presented at COLM) argues claims of LLM introspection are premature. It proposes two necessary conditions — privileged access (not solvable from input cues) and second-order computation — then re-examines two paradigms: input-only classifiers match models' self-state predictions, and models can't reliably distinguish internal tampering from input manipulation, suggesting generic anomaly detection rather than true introspection. Conclusion: current evidence is insufficient.
Related event: Researchers to Challenge Anthropic's Claims of LLM Introspection at COLM(3 posts)→
More from Research
- Boltz Lab reveals 50x molecular token growth in 5 months as Series A closes — GabriCorso · 2026-11-19
- Researcher calls METR/Anthropic '2x speedup' RSI analysis statistically dubious — jessi_cata · 2026-11-19
- Linear Probes Could Reveal Which Persona a Base Model Is Playing, Researchers Suggest — cephaloform · 2026-11-19
- ETH's Anymal robot completes 10km autonomous alpine hike with VLM-guided ROAM system — ChongZzZhang · 2026-11-19
- OpenVax codebase grows from 78K to 565K lines in 15 months — iskander · 2026-11-19
- François Fleuret: decoder transformer's elegance — no trade-off hyperparameters — francoisfleuret · 2026-11-19