[2508.14802] Privileged Self-Access Matters for Introspection in AI

Abstract:Whether AI models can introspect is an increasingly important practical question. But there is no consensus on how introspection is to be defined. Beginning from a recently proposed ''lightweight'' definition, we argue instead for a thicker one. According to our proposal, introspection in AI is any process which yields information about internal states through a process more reliable than one with equal or lower computational cost available to a third party. Using experiments where LLMs reason about their internal temperature parameters, we show they can appear to have lightweight introspection while failing to meaningfully introspect per our proposed definition.

Privileged Self-Access Matters for Introspection in AI Siyuan Song1 Harvey Lederman1 siyuansong@utexas.edu harvey.lederman@utexas.edu Jennifer Hu2∗…

saved by

• Lydia Nottingham
• Chris Shi

related reading

• [2607.14111] Introspection Fine-Tuning (IFT): Training Small LLMs to Introspectarxiv.org
• Training Language Models to Explain Their Own Computationsarxiv.org
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• Can LLMs Introspect? A Reality Checkarxiv.org
• Emergent introspective awareness in large language models \ Anthropicanthropic.com
• Emergent Introspection in AI is Content-Agnosticarxiv.org
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• [2501.11120] Tell me about yourself: LLMs are aware of their learned behaviorsarxiv.org
• Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
• [2508.14802] Privileged Self-Access Matters for Introspection in AIarxiv.org
• Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org