# Does It Make Sense to Speak of Introspection in Large Language Models?

arXiv: https://arxiv.org/abs/2506.05068 · HTML: https://mlsanity.com/paper/2506.05068/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 51 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions](https://mlsanity.com/paper/2310.15421/) (2023)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness](https://mlsanity.com/paper/2308.08708/) (2023)
- [Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving](https://mlsanity.com/paper/2405.12205/) (2024)
- [Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs](https://mlsanity.com/paper/2407.04694/) (2024)
- [Self-Evaluation Improves Selective Generation in Large Language Models](https://mlsanity.com/paper/2312.09300/) (2023)
- [Could a Large Language Model be Conscious?](https://mlsanity.com/paper/2303.07103/) (2023)
- [Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs](https://mlsanity.com/paper/2305.14279/) (2023)
- [Towards Evaluating AI Systems for Moral Status Using Self-Reports](https://mlsanity.com/paper/2311.08576/) (2023)
- [The feasibility of artificial consciousness through the lens of neuroscience](https://mlsanity.com/paper/2306.00915/) (2023)
- [Self-Recognition in Language Models](https://mlsanity.com/paper/2407.06946/) (2024)
- [Simulacra as Conscious Exotica](https://mlsanity.com/paper/2402.12422/) (2024)
- [From Imitation to Introspection: Probing Self-Consciousness in Language Models](https://mlsanity.com/paper/2410.18819/) (2024)
- [Intrinsic Robotic Introspection: Learning Internal States From Neuron Activations](https://mlsanity.com/paper/2011.01880/) (2020)
- [Introspective Perception for Mobile Robots](https://mlsanity.com/paper/2306.16698/) (2023)

## Built on by (most cited first, 25 of 25)

- [Verbalizable Representations Form a Global Workspace in Language Models](https://mlsanity.com/paper/2607.15495/) (2026)
- [Training Language Models to Explain Their Own Computations](https://mlsanity.com/paper/2511.08579/) (2025)
- [Privileged Self-Access Matters for Introspection in AI](https://mlsanity.com/paper/2508.14802/) (2025)
- [Counterfactual Simulation Training for Chain-of-Thought Faithfulness](https://mlsanity.com/paper/2602.20710/) (2026)
- [A validity-guided workflow for robust large language model research in psychology](https://mlsanity.com/paper/2507.04491/) (2025)
- [Know Thyself? On the Incapability and Implications of AI Self-Recognition](https://mlsanity.com/paper/2510.03399/) (2025)
- [Emergent Introspection in AI is Content-Agnostic](https://mlsanity.com/paper/2603.05414/) (2026)
- [Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns](https://mlsanity.com/paper/2509.24988/) (2025)
- [Language models recognize dropout and Gaussian noise applied to their activations](https://mlsanity.com/paper/2604.17465/) (2026)
- [Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision](https://mlsanity.com/paper/2606.32038/) (2026)
- [Minimal and Mechanistic Conditions for Behavioral Self-Awareness in LLMs](https://mlsanity.com/paper/2511.04875/) (2025)
- [Fine-Tuning Language Models to Know What They Know](https://mlsanity.com/paper/2602.02605/) (2026)
- [Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement](https://mlsanity.com/paper/2607.04277/) (2026)
- [Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation](https://mlsanity.com/paper/2603.18893/) (2026)
- [On the Creativity of AI Agents](https://mlsanity.com/paper/2604.13242/) (2026)
- [AI and Consciousness: Shifting Focus Towards Tractable Questions](https://mlsanity.com/paper/2605.06965/) (2026)
- [Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs](https://mlsanity.com/paper/2605.07806/) (2026)
- [Metacognition in LLMs: Foundations, Progress, and Opportunities](https://mlsanity.com/paper/2607.11881/) (2026)
- [LLM Self-Explanations Fail Semantic Invariance](https://mlsanity.com/paper/2603.01254/) (2026)
- [The Shared Latent Structure of LLM Psychometric Responses](https://mlsanity.com/paper/2605.05080/) (2026)
- [Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory](https://mlsanity.com/paper/2607.23927/) (2026)
- [Asymmetric Communication: Large Language Models and Language Games](https://mlsanity.com/paper/2607.28137/) (2026)
- [Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models](https://mlsanity.com/paper/2608.13258/) (2026)
- ["As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It](https://mlsanity.com/paper/2609.25021/) (2026)
- [Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs](https://mlsanity.com/paper/2610.20179/) (2026)

## Abstract (arXiv)

Large language models (LLMs) exhibit compelling linguistic behaviour, and sometimes offer self-reports, that is to say statements about their own nature, inner workings, or behaviour. In humans, such reports are often attributed to a faculty of introspection and are typically linked to consciousness. This raises the question of how to interpret self-reports produced by LLMs, given their increasing linguistic fluency and cognitive capabilities. To what extent (if any) can the concept of introspection be meaningfully applied to LLMs? Here, we present and critique two examples of apparent introspective self-report from LLMs. In the first example, an LLM attempts to describe the process behind its own "creative" writing, and we argue this is not a valid example of introspection. In the second example, an LLM correctly infers the value of its own temperature parameter, and we argue that this can be legitimately considered a minimal example of introspection, albeit one that is (presumably) not accompanied by conscious experience.