The DOI matches its Crossref record.
Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“this “metacognitive space” captures only a fraction of the full neural dimensionality.”
From Self-Referential Introspection in Large Language Models: The Critical Threshold for Recursive Self-Improvement (2026) · cites this paper as [53]
In the citing paper
“Li et al. [53] demonstrated that while LLMs can monitor a low-dimensional projection of their activation space”
From Self-Referential Introspection in Large Language Models: The Critical Threshold for Recursive Self-Improvement (2026) · cites this paper as [53]
Citations
Cites
Still being checked.
Cited by
Zhang, J., Yuan, B., & Zhang, Q. (2026) · Entropy · doi:10.3390/e28090951 · Cited by 2
Metadata
- Authors
- Li, J.-A., Xiong, H., Wilson, R., Mattar, M. G., & Benna, M. K.
- Affiliations
- University of California San Diego (US)
- Georgia Tech
- Georgia Institute of Technology (US)
- New York University (US)
- Venue
- Advances in Neural Information Processing Systems 38
- Published
- 2025
- Pages
- 66858-66893
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7196935144
- Cited by
- 1
- References
- 0
- Citations by year
- 2026: 1
- FWCI
- 0.95
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neurobiology of Language and Bilingualism
- Keywords
- language models, metacognition, metacognitive monitoring, metacognitive regulation, internal activations, self-regulation, large language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations. https://app.cochat.ai/papers/10.52202/085713-2009
- The paper
- Li, J.-A., Xiong, H., Wilson, R., Mattar, M. G., & Benna, M. K. (2025). Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations. Advances in Neural Information Processing Systems 38. https://doi.org/10.52202/085713-2009
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.