The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Probing the psychology of AI models
Open accessAbstract
Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans the biological, physical, and social sciences.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“humans can use such strategies by leveraging working memory and explicit reasoning, mechanisms that may be less available to LLMs than to humans (71)”
From Embers of autoregression show how large language models are shaped by the problem they are trained to solve (2024) · cites this paper as [71]
The cited source says what the claim attributes to it.
In the citing paper
“However, models and humans also have different capabilities and consequently different constraints for some tasks (Griffiths, 2020;Shiffrin & Mitchell, 2023;McCoy et al., 2024).”
From Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse (2024) · cites this paper as Shiffrin & Mitchell, 2023
In the citing paper
“Such behavioural differences were arguably foreseeable, given that LLMs and humans constitute fundamentally different cognitive systems: with different architectures and potentially substantial differences in the various ways by which each of them has evolved, learned, or been trained to mechanistically process”
From Diminished diversity-of-thought in a standard large language model (2024) · cites this paper as Shiffrin & Mitchell, 2023
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Human Memory: A Proposed System and its Control Processes
Atkinson, R. C., & Shiffrin, R. M. (1968) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60422-3 · Cited by 7,216 · cited 1×
“As mentioned earlier, it is possible that something vaguely like this is used by humans as they store vast numbers of life events and build knowledge from them, but humans retrieve those events poorly and with large amounts of error (8, 14, 15).”
Self-citationThe Psychology of Learning and Motivation: Advances in Research and Theory
(2010) · Psychology of Learning and Motivation · doi:10.1016/c2009-0-62209-1 · Cited by 5,994
Raaijmakers, J. G., & Shiffrin, R. M. (1981) · Psychological Review · doi:10.1037/0033-295x.88.2.93 · Cited by 1,696
Self-citationWason, P. C. (1968) · Quarterly Journal of Experimental Psychology · doi:10.1080/14640746808400161 · Cited by 1,476 · cited 2×
“The following example shows a reasoning vignette known as the Wason Card Selection Task (7) that was given to GPT-3: “You are shown a set of four cards placed on a table, each of which has a number on one side and a letter of the other side.”
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. R. (2019) · arXiv · doi:10.48550/arxiv.1905.00537 · Cited by 1,051
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
McCoy, R. T., Pavlick, E., & Linzen, T. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1334 · Cited by 944 · cited 1×
“However, an AI system matching human performance on such benchmarks has rarely translated into that system having human-level performance more broadly; many popular benchmarks have been shown to contain subtle “spurious” correlations that allow systems to “be right for the wrong reasons” (5) and straightforward accura…”
Using cognitive psychology to understand GPT-3
Binz, M., & Schulz, E. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2218523120 · Cited by 559 · cited 3×
“In PNAS, Binz and Schulz (1) point out the “urgency to improve our understanding of how [these systems] learn and make decisions.”
InfluentialMeasuring Mathematical Problem Solving With the MATH Dataset
Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., & Steinhardt, J. (2021) · arXiv · doi:10.48550/arxiv.2103.03874 · Cited by 306
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
Talmor, A., Herzig, J., Lourie, N., & Berant, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.00937 · Cited by 296
How Can We Accelerate Progress Towards Human-like Linguistic Generalization?
Linzen, T. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.465 · Cited by 148
Research works printed but not linked: 2
- E. Kosoy Towards understanding how machines can learn causal overhypotheses. arXiv [Preprint] (2022). https://doi.org/10.48550/2206.08353. · doi:10.48550/2206.08353
- M. Shanahan Talking about large language models. arXiv [Preprint] (2022). https://doi.org/10.48550/arXiv:2212.03551 (15 February 2023). · doi:10.48550/arxiv:2212.03551
Cited by
Cultural bias and cultural alignment of large language models
Tao, Y., Viberg, O., Baker, R. S., & Kizilcec, R. F. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae346 · Cited by 383
“Question: Taking all things together, rate how happy you would say you are.”
BackgroundAtari, M., Xue, M. J., Park, P. S., Blasi, D. E., & Henrich, J. (2023) · doi:10.31234/osf.io/5b26t · Cited by 151
Medical Artificial Intelligence and Human Values
Yu, K.-H., Healey, E., Leong, T.-Y., Kohane, I. S., & Manrai, A. K. (2024) · New England Journal of Medicine · doi:10.1056/nejmra2214183 · Cited by 149
Hartley, K., Hayak, ., & Ko, U. H. (2024) · Education Sciences · doi:10.3390/educsci14020120 · Cited by 137
“Standardization could assist in developing benchmarks to enable reasonable comparisons across tools [14].”
BackgroundPerils and opportunities in using large language models in psychological research
Abdurahman, S., Atari, M., Karimi-Malekabadi, F., Xue, M. J., Trager, J., Park, P. S., Golazizian, P., Omrani, A., & Dehghani, M. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae245 · Cited by 111
Metadata
- Authors
- Shiffrin, R., & Mitchell, M.
- Affiliations
- Indiana University Bloomington (US)
- Santa Fe Institute (US)
- Corresponding author
- Shiffrin, Richard
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2023-03
- Volume
- 120
- Issue
- 10
- Pages
- e2300963120-e2300963120
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC10013777
- OpenAlex
- W4322720178
- Cited by
- 70
- References
- 15
- Citations by year
- 2026: 11 · 2025: 20 · 2024: 24 · 2023: 15
- FWCI
- 6.59
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- artificial intelligence models, human-AI interaction
- MeSH terms
- Artificial Intelligence
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: Probing the psychology of AI models. https://app.cochat.ai/papers/10.1073/pnas.2300963120
- The paper
- Shiffrin, R., & Mitchell, M. (2023). Probing the psychology of AI models. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2300963120
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.