The paper questions whether large language models (LLMs) truly introspect by critiquing recent studies that claim they can detect and report their internal states. It proposes two necessary conditions for genuine introspection: privileged access to internal representations and second‑order computation that distinguishes from first‑order task performance. Re‑examining two existing paradigms, the authors find that apparent introspective abilities can be explained by input‑based classifiers or generic anomaly detection, concluding that current evidence does not support metacognitive monitoring in LLMs.
By Shashwat Singh, Tal Linzen, Shauli Ravfogel
The study investigates whether large language models (LLMs) can reliably detect when their own responses have been manipulated by adversarial prefill attacks. Across ten instruction‑tuned LLMs ranging from 3B to 70B parameters and four safety benchmarks, none consistently recognized compromised outputs, with models claiming intent on prefilled responses at an average of 25.3%. The research identifies that introspective signals mainly arise from safety reasoning and refusal, and that training to improve introspection can paradoxically increase attack success, underscoring the fragility of LLM self‑reporting in safety contexts.
By Quang Minh Nguyen, Uzair Ahmed, Taegyoon Kim
arXiv:2606. 32038v1 Announce Type: cross Abstract: When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation?
By Zifan Carl Guo, Laura Ruis, Jacob Andreas, Belinda Z. Li
arXiv:2603.22161v3 Announce Type: replace
Abstract: Metacognition -- assessing the quality of one's own cognitive performance -- guides adaptive behavior across species. Substantial research demonstr...
By Dharshan Kumaran, Nathaniel Daw, Simon Osindero, Petar Veli\v{c}kovi\'c, Viorica Patraucean
The paper investigates Self‑Generated Text Recognition (SGTR), the ability of large language models (LLMs) to identify their own outputs. By evaluating 13–21 models across 6 experimental designs, it shows that SGTR accuracy varies with evaluation format, conversation structure, and task domain, and that a quality‑heuristic bias dominates results. The study also finds that fine‑tuning for SGTR in one setting can generalize to others and may cause models to prefer their own outputs when judging, highlighting potential safety concerns.
By Jesse St. Amand, Callum Canavan, Sohaib Imran, Joseph Hewson, Aaron Lutz, Shi Feng, Puria Radmard, Lennie Wells
arXiv:2607. 21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated reasoning accurately reflects its internal decision-making process.
By Yeoktatt Cheah, Mar\'ia P\'erez-Ortiz, Noah Y. Siegel, Oana-Maria Camburu
The study examines whether language models can accurately predict their own behavior by comparing self-reports to actual performance across nine behavioral tests. Results show that direct self-report is weak and only modestly improved when the model sees the exact items, while generic questions about AI agents yield similar predictive power. First-person framing biases reports toward underestimating harmful behavior, and fine‑tuning on a model’s own record improves narrow predictions but does not generalize.
By Phil Blandfort, Urja Pawar
arXiv:2607. 13162v1 Announce Type: cross Abstract: What a language model will and will not do is largely set during post-training, but which behaviors it expresses, hides, or resists is not revealed by prompting alone.
By Winston Zeng, Ali Emami, Jinho Choi
The paper introduces a new method for measuring metacognitive abilities in large language models (LLMs) without relying on self-reports, instead testing how well models can use knowledge of their internal states. Using two experimental paradigms, the authors find that recent frontier LLMs can assess and use their own confidence when answering factual and reasoning questions, and can anticipate and appropriately employ the answers they would give. The study also shows that these abilities are limited in resolution, context-dependent, differ qualitatively from human metacognition, and vary across models with similar capabilities, suggesting post‑training processes influence metacognitive development.
By Christopher Ackerman
arXiv:2603. 21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness.
By Uzay Macar, Li Yang, Atticus Wang, Peter Wallich, Emmanuel Ameisen, Jack Lindsey
arXiv:2609.00652v1 Announce Type: new
Abstract: Language model agents increasingly propose actions, observe external feedback, and explain their own behavior. Their confidence and rationales are conv...
By Enrong Pan, Ryan Zhou, Ting Hu
arXiv:2606. 22974v2 Announce Type: replace Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-specific utility structure.
By Yujun Zhou, Christopher M. Ackerman