Studying and improving reasoning in humans and machines
Open accessAbstract
In the present study, we investigate and compare reasoning in large language models (LLMs) and humans, using a selection of cognitive psychology tools traditionally dedicated to the study of (bounded) rationality. We presented to human participants and an array of pretrained LLMs new variants of classical cognitive experiments, and cross-compared their performances. Our results showed that most of the included models presented reasoning errors akin to those frequently ascribed to error-prone, heuristic-based human reasoning. Notwithstanding this superficial similarity, an in-depth comparison between humans and LLMs indicated important differences with human-like reasoning, with models’ limitations disappearing almost entirely in more recent LLMs’ releases. Moreover, we show that while it is possible to devise strategies to induce better performance, humans and machines are not equally responsive to the same prompting schemes. We conclude by discussing the epistemological implications and challenges of comparing human and machine behavior for both artificial intelligence and cognitive psychology.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Yax et al. found that scores for some tests significantly decreased.
“Their analyses also found that, surprisingly, the scores for some of the tests significantly decreased, exemplifying the reliability issues with proprietary LLMs.”
From How should the advancement of large language models affect the practice of science? (2025) · cites this paper as [40]
Yax et al. found that the results of proprietary LLMs (ChatGPT and GPT4) could not be replicated three months after the initial experiments.
“Likewise, this has been observed by Yax et al. (40) who tested the reasoning capabilities of LLMs, and found that the results of proprietary LLMs, i.e., ChatGPT and GPT4, could not be replicated three months after the initial experiments.”
From How should the advancement of large language models affect the practice of science? (2025) · cites this paper as [40]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
R: A Language and Environment for Statistical Computing
R Core Team (2000) · doi:10.32614/r.manuals · Cited by 355,706 · see citing works
Fitting Linear Mixed-Effects Models Using <b>lme4</b>
Bates, D., Mächler, M., Bolker, B., & Walker, S. (2015) · Journal of Statistical Software · doi:10.18637/jss.v067.i01 · Cited by 86,835 · see citing works
Tversky, A., & Kahneman, D. (1974) · Science · doi:10.1126/science.185.4157.1124 · Cited by 28,810 · cited 3× · see citing works
“If a dataset has a Digital Object Identifier (DOI) as its unique identifier, we strongly encourage including this in the Reference list and citing the dataset in the Data Availability Statement.”
InfluentialReinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · see citing works
Judgment under Uncertainty: Heuristics and Biases
Tversky, A., & Kahneman, D. (1975) · Utility, Probability, and Human Decision Making · doi:10.1007/978-94-010-1834-0_8 · Cited by 22,650 · see citing works
Wickham, H., Averick, M., Bryan, J., Chang, W., McGowan, L., François, R., Grolemund, G., Hayes, A., Henry, L., Hester, J., et al. (2019) · Journal of Open Source Software · doi:10.21105/joss.01686 · Cited by 22,138 · see citing works
ChatGPT for good? On opportunities and challenges of large language models for education
Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G., Günnemann, S., Hüllermeier, E., et al. (2023) · Learning and Individual Differences · doi:10.1016/j.lindif.2023.102274 · Cited by 7,326 · see citing works
Kahneman, D., & Tversky, A. (1984) · American Psychologist · doi:10.1037/0003-066x.39.4.341 · Cited by 6,544 · see citing works
Cognitive Reflection and Decision Making
Frederick, S. (2005) · Journal of Economic Perspectives · doi:10.1257/089533005775196732 · Cited by 5,256 · see citing works
Administrative Behavior: A Study of Decision-Making Processes in Administrative Organization.
Brown, M., & Simon, H. A. (1978) · Contemporary Sociology A Journal of Reviews · doi:10.2307/2065048 · Cited by 4,807 · see citing works
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263 · see citing works
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208 · see citing works
Allais, M. (1953) · Econometrica · doi:10.2307/1907921 · Cited by 4,054 · see citing works
Extensional versus intuitive reasoning: The conjunction fallacy in probability judgment.
Tversky, A., & Kahneman, D. (1983) · Psychological Review · doi:10.1037/0033-295x.90.4.293 · Cited by 3,991 · see citing works
Neural Information Processing Systems
(2018) · The MIT Press eBooks · doi:10.7551/mitpress/11474.003.0014 · Cited by 3,775 · see citing works
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676 · see citing works
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.18223 · Cited by 2,090
Performance-optimized hierarchical models predict neural responses in higher visual cortex
Yamins, D. L. K., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1403112111 · Cited by 1,924 · see citing works
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526 · see citing works
Parameter-efficient fine-tuning of large-scale pre-trained language models
Ding, N., Qin, Y., Yang, G., Wei, F., Yang, Z., Su, Y., Hu, S., Chen, Y., Chan, C.-M., Chen, W., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00626-4 · Cited by 1,191 · see citing works
Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning
Heaton, J. (2017) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-017-9314-z · Cited by 1,062 · see citing works
Training Compute-Optimal Large Language Models
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.15556 · Cited by 929 · see citing works
Assessing miserly information processing: An expansion of the Cognitive Reflection Test
Toplak, M. E., West, R. F., & Stanovich, K. E. (2014) · Thinking & Reasoning · doi:10.1080/13546783.2013.844729 · Cited by 864 · see citing works
Self-Consistency Improves Chain of Thought Reasoning in Language Models
Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2203.11171 · Cited by 829 · see citing works
Out of One, Many: Using Language Models to Simulate Human Samples
Argyle, L. P., Busby, E. C., Fulda, N., Gubler, J. R., Rytting, C., & Wingate, D. (2023) · Political Analysis · doi:10.1017/pan.2023.2 · Cited by 783 · see citing works
Reinforcement learning, fast and slow
Botvinick, M., Ritter, S., Wang, J. X., Kurth-Nelson, Z., Blundell, C., & Hassabis, D. (2019) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2019.02.006 · Cited by 667 · see citing works
Investigating an alternate form of the cognitive reflection test
Thomson, K. S., & Oppenheimer, D. M. (2016) · Judgment and Decision Making · doi:10.1017/s1930297500007622 · Cited by 612 · see citing works
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.04615 · Cited by 569 · see citing works
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× · see citing works
“There are some recent studies on debiasing reasoning in humans that might suggest a more direct way of comparing what humans do with LLMs.”
Prospect Theory in the Wild: Evidence from the Field
Camerer, C. F. (2000) · Cambridge University Press eBooks · doi:10.1017/cbo9780511803475.017 · Cited by 549 · see citing works
Neys, W. D. (2006) · Psychological Science · doi:10.1111/j.1467-9280.2006.01723.x · Cited by 532 · see citing works
Gigerenzer, G., Hertwig, R., & Pachur, T. (2011) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780199744282.001.0001 · Cited by 464 · see citing works
Can AI language models replace human participants?
Dillion, D., Tandon, N., Gu, Y., & Gray, K. (2023) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2023.04.008 · Cited by 405 · see citing works
Dissociating language and thought in large language models
Mahowald, K., Ivanova, A. A., Blank, I. A., Kanwisher, N., Tenenbaum, J. B., & Fedorenko, E. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.01.011 · Cited by 345 · see citing works
The debate over understanding in AI’s large language models
Mitchell, M., & Krakauer, D. C. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2215907120 · Cited by 340 · see citing works
Replicating patterns of prospect theory for decision under risk
Ruggeri, K., Alì, S., Berge, M. L., Bertoldo, G., Bjørndal, L. D., Cortijos‐Bernabeu, A., Davison, C., Demić, E., Serna, C. E., Friedemann, M., et al. (2020) · Nature Human Behaviour · doi:10.1038/s41562-020-0886-x · Cited by 329 · see citing works
Neys, W. D., Vartanian, O. A., & Goel, V. (2008) · Psychological Science · doi:10.1111/j.1467-9280.2008.02113.x · Cited by 241 · see citing works
The Bias Bias in Behavioral Economics
Gigerenzer, G. (2018) · Review of Behavioral Economics · doi:10.1561/105.00000092 · Cited by 213 · see citing works
Cognitive reflection test: Whom, how, when
Brañas‐Garza, P., Kujal, P., & Lenkei, B. (2019) · Journal of Behavioral and Experimental Economics · doi:10.1016/j.socec.2019.101455 · Cited by 146 · see citing works
A Manager and an AI Walk into a Bar: Does ChatGPT Make Biased Decisions Like We Do?
Chen, Y., Kirshner, S. N., Ovchinnikov, A., Andiappan, M., & Jenkin, T. (2025) · Manufacturing & Service Operations Management · doi:10.1287/msom.2023.0279 · Cited by 143 · see citing works
Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models
Tamkin, A., Brundage, M., Clark, J., & Ganguli, D. (2021) · arXiv · doi:10.48550/arxiv.2102.02503 · Cited by 135 · see citing works
Sirota, M., Dewberry, C., Juanchich, M., Valuš, L., & Marshall, A. C. (2020) · Journal of Behavioral Decision Making · doi:10.1002/bdm.2213 · Cited by 117 · see citing works
A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets
Laskar, M. T. R., Bari, M. S., Rahman, M., Bhuiyan, M. A. H., Joty, S., & Huang, J. X. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.29 · Cited by 117 · see citing works
On the reality of the conjunction fallacy
Sides, A., Osherson, D. N., Bonini, N., & Viale, R. (2002) · Memory & Cognition · doi:10.3758/bf03195280 · Cited by 110 · see citing works
Messer, W. S., & Griggs, R. A. (1993) · Bulletin of the Psychonomic Society · doi:10.3758/bf03337322 · Cited by 95 · see citing works
Lessons for artificial intelligence from the study of natural stupidity
Rich, A. S., & Gureckis, T. M. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0038-z · Cited by 94 · see citing works
Language Models as Agent Models
Andreas, J. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022 · doi:10.18653/v1/2022.findings-emnlp.423 · Cited by 92 · see citing works
Understanding Human Intelligence through Human Limitations
Griffiths, T. L. (2020) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2020.09.001 · Cited by 88 · see citing works
Diminished diversity-of-thought in a standard large language model
Park, P. S., Schoenegger, P., & Zhu, C. (2024) · Behavior Research Methods · doi:10.3758/s13428-023-02307-x · Cited by 83 · see citing works
Inducing anxiety in large language models increases exploration and biasPreprint
Coda-Forno, J., Witte, K., Jagadish, A. K., Binz, M., Akata, Z., & Schulz, E. (2023) · arXiv.org · doi:10.48550/arxiv.2304.11111 · Cited by 79 · see citing works
A Manager and an AI Walk into a Bar: Does ChatGPT Make Biased Decisions Like We Do?Preprint
Chen, Y., Kirshner, S. N., Ovchinnikov, A. S., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4380365 · Cited by 76 · see citing works
Language models show human-like content effects on reasoning tasks
Dasgupta, I., Lampinen, A. K., Chan, S. C. Y., Sheahan, H. R., Creswell, A., Kumaran, D., McClelland, J. L., & Hill, F. (2022) · arXiv · doi:10.48550/arxiv.2207.07051 · Cited by 53 · see citing works
Using proprietary language models in academic research requires explicit justification
Palmer, A., Smith, N. A., & Spirling, A. (2023) · Nature Computational Science · doi:10.1038/s43588-023-00585-1 · Cited by 51 · see citing works
Computational Language Modeling and the Promise of In Silico Experimentation
Jain, S., Vo, V. A., Wehbe, L., & Huth, A. G. (2023) · Neurobiology of Language · doi:10.1162/nol_a_00101 · Cited by 37 · see citing works
Thinking Fast and Slow in Large Language Models
Hagendorff, T., Fabi, S., & Kosiński, M. (2022) · PubMed Central · doi:10.48550/arxiv.2212.05206 · Cited by 36 · see citing works
Summerfield, C. (2022) · doi:10.1093/oso/9780192843883.001.0001 · Cited by 23 · see citing works
Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?Preprint
Horton, J. J., Filippas, A., & Manning, B. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4413859 · Cited by 12 · see citing works
Measuring individual differences in cognitive effort avoidance.
Juvina, I., Nador, J., Larue, O., Green, R., Harel, A., & Minnery, B. S. (2018) · Journal of Bioresource Management · Cited by 9 · see citing works
Rationality and the reflective mind: A case for typical performance measure of cognitive ability
Ganuthula, V. R. R., & Dyaram, L. (2016) · Learning and Individual Differences · doi:10.1016/j.lindif.2016.06.019 · Cited by 5 · see citing works
Hierarchical organization of language predictions in the brain
(2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01534-8 · Cited by 3 · see citing works
Hertwig (1999) · doi:10.1002/(sici)1099-0771(199912)12:4
OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.08774
Flagged first, then by citations
Research works printed but not linked: 9
- [6]Thaler, R. & Sunstein, C. NUDGE: Improving Decisions About Health, Wealth, and Happiness. Nudge: Improving Decisions about Health, Wealth, and Happiness vol. 47 (2009).
- [10]von Neumann, J., Morgenstern, O. & Rubinstein, A. Theory of Games and Economic Behavior (60th Anniversary Commemorative Edition). (Princeton University Press, 1944).
- [21]Brown, T. B. et al. Language models are few-shot learners. In Proc 33rd Conference on Neural Information Processing Systems (2020).
- [30]Kojima, T., Gu, S. S., Reid, M., Matsuo, Y. & Iwasawa, Y. Large language models are zero-shot reasoners. In Neural Information Processing Systems (2022).
- [31]Piantadosi, S. Modern language models refute Chomsky’s approach to language. Preprint at https://lingbuzz.net/lingbuzz/007180 (2023).
- [38]Aher, G., Arriaga, R. I. & Kalai, A. T. Using large language models to simulate multiple humans and replicate human subject studies. In Proc 40th International Conference on Machine Learning (ICML’23), Vol. 202. JMLR.org, Article 17, 337–371 (2023).
- [54]Gigerenzer, G. Gut Feelings: The Intelligence of the Unconscious. (Penguin Books, 2008).
- [68]Goodfellow, I., Bengio, Y. & Courville, A. Deep learning: The MIT Press. vol. 19 (MIT Press, 2016).
- [72]Binz, M., & Schulz, E. Turning large language models into cognitive models. In Proc International Conference on Learning Representations (2023).
Cited by
Sorted by citations
How human–AI feedback loops alter human perceptual, emotional and social judgements
Glickman, M., & Sharot, T. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-02077-2 · Cited by 289 · see citing works
How should the advancement of large language models affect the practice of science?
Binz, M., Alaniz, S., Roskies, A., Aczel, B., Bergstrom, C. T., Allen, C., Schad, D., Wulff, D., West, J. D., Zhang, Q., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2401227121 · Cited by 74 · see citing works
Hagendorff, T., Dasgupta, I., Binz, M., Chan, S. C. Y., Lampinen, A., Wang, J. X., Akata, Z., & Schulz, E. (2023) · arXiv · doi:10.48550/arxiv.2303.13988 · Cited by 68 · see citing works
Generative artificial intelligence performs rudimentary structural biology modeling
Ille, A. M., Markosian, C., Burley, S. K., Mathews, M. B., Pasqualini, R., & Arap, W. (2024) · Scientific Reports · doi:10.1038/s41598-024-69021-2 · Cited by 16 · see citing works
- Authors
- Yax, N., Anlló, H., & Palminteri, S.
- Affiliations
- Institut national de recherche en sciences et technologies du numérique (FR)
- Inserm (FR)
- Corresponding author
- Palminteri, Stefano
- Venue
- Communications Psychology
- Published
- 2024-06-03
- Volume
- 2
- Issue
- 1
- Pages
- 51-51
- ISSN
- 2731-9121 (ISSN-L)
- PMC
- PMC11332180
- OpenAlex
- W4399300217
- Cited by
- 40
- References
- 62
- Citations by year
- 2026: 14 · 2025: 21 · 2024: 5
- FWCI
- 14.84
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Communications Psychology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- HAL (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- European Commission (HORIZON2020)
- Agence Nationale de la Recherche (ANR-21-CE23-0002, ANR-21-CE28-0024, ANR-21-CE37-0008)
- Grand Équipement National De Calcul Intensif
- HORIZON EUROPE European Research Council (101043804)
- Topics
- Social Sciences › Decision Sciences › General Decision Sciences › Decision-Making and Behavioral Economics
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- large language models, human reasoning, bounded rationality, heuristic reasoning, cognitive psychology experiments, human-AI comparison, prompting strategies, reasoning errors, epistemology of AI
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
