# No Reliable Evidence of Self-Reported Sentience in Small Large Language Models

arXiv: https://arxiv.org/abs/2601.15334 · HTML: https://mlsanity.com/paper/2601.15334/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 23 of 23)

- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [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)
- [The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models](https://mlsanity.com/paper/2601.10387/) (2026)
- [Emergent Introspective Awareness in Large Language Models](https://mlsanity.com/paper/2601.01828/) (2026)
- [Truth is Universal: Robust Detection of Lies in LLMs](https://mlsanity.com/paper/2407.12831/) (2024)
- [Could a Large Language Model be Conscious?](https://mlsanity.com/paper/2303.07103/) (2023)
- [Standards for Belief Representations in LLMs](https://mlsanity.com/paper/2405.21030/) (2024)
- [Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions](https://mlsanity.com/paper/2505.17120/) (2025)
- [Towards Evaluating AI Systems for Moral Status Using Self-Reports](https://mlsanity.com/paper/2311.08576/) (2023)
- [Large Language Models Report Subjective Experience Under Self-Referential Processing](https://mlsanity.com/paper/2510.24797/) (2025)
- [Can LLMs make trade-offs involving stipulated pain and pleasure states?](https://mlsanity.com/paper/2411.02432/) (2024)
- [AI Awareness](https://mlsanity.com/paper/2504.20084/) (2025)
- [Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare](https://mlsanity.com/paper/2509.07961/) (2025)
- [Fresh in memory: Training-order recency is linearly encoded in language model activations](https://mlsanity.com/paper/2509.14223/) (2025)
- [The Societal Response to Potentially Sentient AI](https://mlsanity.com/paper/2502.00388/) (2025)
- [Beyond Mimicry: Preference Coherence in LLMs](https://mlsanity.com/paper/2511.13630/) (2025)

## Built on by (most cited first, 3 of 3)

- [Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models](https://mlsanity.com/paper/2604.25922/) (2026)
- [Metacognition in LLMs: Foundations, Progress, and Opportunities](https://mlsanity.com/paper/2607.11881/) (2026)
- [Language Models Act on Hidden Valence](https://mlsanity.com/paper/2609.35591/) (2026)

## Abstract (arXiv)

Whether language models possess sentience has no empirical answer. But whether they believe themselves to be sentient can, in principle, be tested. We do so by querying several open-weights models about their own consciousness, and then verifying their responses using classifiers trained on internal activations. We draw upon three model families (Qwen, Llama, GPT-OSS) ranging from 0.6 billion to 70 billion parameters, approximately 50 questions about consciousness and subjective experience, and three classification methods from the interpretability literature. First, we find that models consistently deny being sentient: they attribute consciousness to humans but not to themselves. Second, classifiers trained to detect underlying beliefs - rather than mere outputs - provide no clear evidence that these denials are untruthful. Third, within the Qwen family, larger models deny sentience more confidently than smaller ones. These findings contrast with recent work suggesting that models harbour latent beliefs in their own consciousness.