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

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status

[2508.14802] Privileged Self-Access Matters for Introspection in AI Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Artificial Intelligence arXiv:2508.14802 (cs) [Submitted on 20 Aug 2025] Title: Privileged Self-Access Matters for Introspection in AI Authors: Siyuan Song , Harvey Lederman , Jennifer Hu , Kyle Mahowald View a PDF of the paper titled Privileged Self-Access Matters for Introspection in AI, by Siyuan Song and 3 other authors View PDF HTML (experimental) Abstract: Wheth

related reading

• [2508.14802] Privileged Self-Access Matters for Introspection in AIarxiv.org
• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• Emergent introspective awareness in large language models \ Anthropicanthropic.com
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• [2506.05068] Does It Make Sense to Speak of Introspection in Large Language Models?arxiv.org
• [2512.19428] Attention Is Not What You Needarxiv.org
• [2501.11120] Tell me about yourself: LLMs are aware of their learned behaviorsarxiv.org
• Emergent Introspection in AI is Content-Agnosticarxiv.org
• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• [2506.09501] Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inferencearxiv.org
• [2401.05654] Towards Conversational Diagnostic AIarxiv.org
• [2406.17583] Towards Compositional Interpretability for XAIarxiv.org