[2506.05068] Does It Make Sense to Speak of Introspection in Large Language Models?

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 Get status notifications via email or slack

[2506.05068] Does It Make Sense to Speak of Introspection in Large Language Models? Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2506.05068 (cs) [Submitted on 5 Jun 2025 ( v1 ), last revised 6 Jun 2025 (this version, v2)] Title: Does It Make Sense to Speak of Introspection in Large Language Models? Authors: Iulia M. Comsa , Murray Shanahan View a PDF of the paper titled Does It Make Sense to Speak of Introspection in Large Language Models?, by Iuli

related reading

• Emergent introspective awareness in large language models \ Anthropicanthropic.com
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• [2508.14802] Privileged Self-Access Matters for Introspection in AIarxiv.org
• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• [2508.14802] Privileged Self-Access Matters for Introspection in AIarxiv.org
• [2309.01809] Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
• [2601.01828] Emergent Introspective Awareness in Large Language Modelsarxiv.org
• Can LLMs Introspect? A Reality Checkarxiv.org
• [2503.10965] Auditing language models for hidden objectivesarxiv.org
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• [2506.09501] Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inferencearxiv.org