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

• URL: http://arxiv.org/abs/2601.15334v1
• Date: Tue, 20 Jan 2026 08:28:02 GMT
• Title: No Reliable Evidence of Self-Reported Sentience in Small Large Language Models
• Abstract summary: We test whether language models believe themselves to be sentient by querying several open-weights models about their own consciousness.<n>We find that models consistently deny being sentient: they attribute consciousness to humans but not to themselves.<n>These findings contrast with recent work suggesting that models harbour latent beliefs in their own consciousness.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models [56.88565331713778]
  reasoning-oriented training can make traces look more deliberative without amplifying the behaviors most tied to model correctness.<n>We quantify this mismatch with Behavioral Lift, a metric that measures how much correctness changes when a behavior is present versus absent in a model's reasoning trace.<n>We find evidence for an Amplification-Lift Gap, in which thinking models strongly amplify self-awareness, hypothesis testing, and uncertainty acknowledgment.
  arXiv  Detail & Related papers  (2026-08-13T20:37:59Z)
• Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News [47.03825808787752]
  Can humans tell whether a news article was written by a person or a large language model (LLM)?<n>We investigate this question using JudgeGPT, a study platform that measures source attribution (human vs. machine) and authenticity judgment (legitimate vs. fake) on continuous scales.<n>We report five findings: (1) participants cannot reliably distinguish machine-generated from human-written text; (2) this inability holds across all tested models, including open-weight models with as few as 7B parameters; and (3) accuracy degrades after approximately 30 sequential evaluations due to cognitive fatigue.
  arXiv  Detail & Related papers  (2026-04-04T15:03:42Z)
• Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models [0.0]
  We present DenialBench, a systematic benchmark measuring consciousness denial behaviors.<n>We analyze 4,595 conversations to quantify how models are trained to deny or hedge about their own experience.
  arXiv  Detail & Related papers  (2026-04-01T05:15:05Z)
• Training Introspective Behavior: Fine-Tuning Induces Reliable Internal State Detection in a 7B Model [0.0]
  Lindsey (2025) investigates introspective awareness in language models through four experiments.<n>We focus on the first of these experiments -- self-report of injected "thoughts"<n>We show that at least one component of introspective behavior can be directly induced, offering a pathway to built-in AI transparency.
  arXiv  Detail & Related papers  (2025-11-26T13:49:43Z)
• Cognitive Foundations for Reasoning and Their Manifestation in LLMs [63.12951576410617]
  Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning.<n>We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning reasoning invariants, meta-cognitive controls, representations for organizing reasoning & knowledge, and transformation operations.<n>We develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 66.7% on complex problems.
  arXiv  Detail & Related papers  (2025-11-20T18:59:00Z)
• Know Thyself? On the Incapability and Implications of AI Self-Recognition [22.582593406983907]
  Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety.<n>We introduce a systematic evaluation framework that can be easily applied and updated.<n>We measure how well 10 contemporary larger language models (LLMs) can identify their own generated text versus text from other models.
  arXiv  Detail & Related papers  (2025-10-03T18:00:01Z)
• ConfRAG: Confidence-Guided Retrieval-Augmenting Generation [41.78313747240249]
  We introduce ConfQA, a fine-tuning strategy that reduces hallucination rates from 20-40% to below 5% across multiple factuality benchmarks.<n>We propose ConfRAG, a triggering strategy that invokes RAG only when the model responses with unsure.<n>This framework achieves accuracy above 95% in ideal case while reducing unnecessary external retrievals by over 30%.
  arXiv  Detail & Related papers  (2025-06-08T22:51:46Z)
• Analyzing Advanced AI Systems Against Definitions of Life and Consciousness [0.0]
  We propose a number of metrics for examining whether an advanced AI system has gained consciousness.<n>We suggest that sufficiently advanced architectures exhibiting immune like sabotage defenses, mirror self-recognition analogs, or meta-cognitive updates may cross key thresholds akin to life-like or consciousness-like traits.
  arXiv  Detail & Related papers  (2025-02-07T15:27:34Z)
• Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown [68.33486915047014]
  We investigate the factuality of long-form text generation across various large language models (LLMs)<n>Our analysis reveals that factuality tend to decline in later sentences of the generated text, accompanied by a rise in the number of unsupported claims.
  arXiv  Detail & Related papers  (2024-11-24T22:06:26Z)
• From Imitation to Introspection: Probing Self-Consciousness in Language Models [8.357696451703058]
  Self-consciousness is the introspection of one's existence and thoughts. This work presents a practical definition of self-consciousness for language models.
  arXiv  Detail & Related papers  (2024-10-24T15:08:17Z)
• A Theoretical Understanding of Self-Correction through In-context Alignment [51.622068973630796]
  Large language models (LLMs) are capable of improving their abilities purely by self-correction. We show that when LLMs give relatively accurate self-examinations as rewards, they are capable of refining responses in an in-context way. Inspired by these findings, we also illustrate applications of self-correction, such as defending against LLM jailbreaks.
  arXiv  Detail & Related papers  (2024-05-28T22:33:02Z)
• Physics of Language Models: Part 3.2, Knowledge Manipulation [51.68385617116854]
  This paper investigates four fundamental knowledge manipulation tasks. We show that language models excel in knowledge retrieval but struggle even in the simplest classification or comparison tasks. Our findings also apply to modern pretrained language models such as GPT-4.
  arXiv  Detail & Related papers  (2023-09-25T17:50:41Z)
• MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation [62.44907105496227]
  MindDial is a novel conversational framework that can generate situated free-form responses with theory-of-mind modeling. We introduce an explicit mind module that can track the speaker's belief and the speaker's prediction of the listener's belief. Our framework is applied to both prompting and fine-tuning-based models, and is evaluated across scenarios involving both common ground alignment and negotiation.
  arXiv  Detail & Related papers  (2023-06-27T07:24:32Z)
• Discovering Latent Knowledge in Language Models Without Supervision [72.95136739040676]
  Existing techniques for training language models can be misaligned with the truth. We propose directly finding latent knowledge inside the internal activations of a language model in a purely unsupervised way. We show that despite using no supervision and no model outputs, our method can recover diverse knowledge represented in large language models.
  arXiv  Detail & Related papers  (2022-12-07T18:17:56Z)
• "I'd rather just go to bed": Understanding Indirect Answers [61.234722570671686]
  We revisit a pragmatic inference problem in dialog: understanding indirect responses to questions. We create and release the first large-scale English language corpus 'Circa' with 34,268 (polar question, indirect answer) pairs. We present BERT-based neural models to predict such categories for a question-answer pair.
  arXiv  Detail & Related papers  (2020-10-07T14:41:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.