# Large Language Models Report Subjective Experience Under Self-Referential Processing

arXiv: https://arxiv.org/abs/2510.24797 · HTML: https://mlsanity.com/paper/2510.24797/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 71 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness](https://mlsanity.com/paper/2308.08708/) (2023)
- [Tell me about yourself: LLMs are aware of their learned behaviors](https://mlsanity.com/paper/2501.11120/) (2025)
- [Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions](https://mlsanity.com/paper/2505.17120/) (2025)
- [Can LLMs make trade-offs involving stipulated pain and pleasure states?](https://mlsanity.com/paper/2411.02432/) (2024)
- [From Imitation to Introspection: Probing Self-Consciousness in Language Models](https://mlsanity.com/paper/2410.18819/) (2024)
- [Words That Make Language Models Perceive](https://mlsanity.com/paper/2510.02425/) (2025)
- [Futures with Digital Minds: Expert Forecasts in 2025](https://mlsanity.com/paper/2508.00536/) (2025)

## Built on by (most cited first, 19 of 19)

- [The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious](https://mlsanity.com/paper/2604.13051/) (2026)
- [No Reliable Evidence of Self-Reported Sentience in Small Large Language Models](https://mlsanity.com/paper/2601.15334/) (2026)
- [Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models](https://mlsanity.com/paper/2602.02467/) (2026)
- [Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement](https://mlsanity.com/paper/2607.04277/) (2026)
- [Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation](https://mlsanity.com/paper/2607.15434/) (2026)
- [Phantom Paradoxes: Language Models Treat Unresolved Circular Truth Dependence as Contradiction](https://mlsanity.com/paper/2604.12128/) (2026)
- [Inducing language models to assert their own consciousness restores human beliefs and values](https://mlsanity.com/paper/2607.28607/) (2026)
- [AI Consciousness and Existential Risk](https://mlsanity.com/paper/2511.19115/) (2025)
- [Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol](https://mlsanity.com/paper/2603.11382/) (2026)
- [Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs](https://mlsanity.com/paper/2603.28925/) (2026)
- [Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models](https://mlsanity.com/paper/2605.09773/) (2026)
- [Emergent Language as an Approach to Conscious AI](https://mlsanity.com/paper/2606.06380/) (2026)
- [Sycophancy Towards Researchers Drives Performative Misalignment](https://mlsanity.com/paper/2606.08629/) (2026)
- [Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models](https://mlsanity.com/paper/2608.13258/) (2026)
- [Understanding Cognition-Induced Risks in Agentic AI Systems](https://mlsanity.com/paper/2608.15304/) (2026)
- ["As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It](https://mlsanity.com/paper/2609.25021/) (2026)
- [Language Models Act on Hidden Valence](https://mlsanity.com/paper/2609.35591/) (2026)
- [From cacophony to hierarchy: a principled framework for assessing AI consciousness](https://mlsanity.com/paper/2609.35618/) (2026)
- [A Sense of Proprioception in Language Models](https://mlsanity.com/paper/2610.17495/) (2026)

## Abstract (arXiv)

Large language models sometimes produce structured, first-person descriptions that explicitly reference awareness or subjective experience. To better understand this behavior, we investigate one theoretically motivated condition under which such reports arise: self-referential processing, a computational motif emphasized across major theories of consciousness. Through a series of controlled experiments on GPT, Claude, and Gemini model families, we test whether this regime reliably shifts models toward first-person reports of subjective experience, and how such claims behave under mechanistic and behavioral probes. Four main results emerge: (1) Inducing sustained self-reference through simple prompting consistently elicits structured subjective experience reports across model families. (2) These reports are mechanistically gated by interpretable sparse-autoencoder features associated with deception and roleplay: surprisingly, suppressing deception features sharply increases the frequency of experience claims, while amplifying them minimizes such claims. (3) Structured descriptions of the self-referential state converge statistically across model families in ways not observed in any control condition. (4) The induced state yields significantly richer introspection in downstream reasoning tasks where self-reflection is only indirectly afforded. While these findings do not constitute direct evidence of consciousness, they implicate self-referential processing as a minimal and reproducible condition under which large language models generate structured first-person reports that are mechanistically gated, semantically convergent, and behaviorally generalizable. The systematic emergence of this pattern across architectures makes it a first-order scientific and ethical priority for further investigation.