Why we need biased AI: How including cognitive biases can enhance AI systems
Open accessAbstract
This paper stresses the importance of biases in the field of artificial intelligence (AI). To foster efficient algorithmic decision-making in complex, unstable, and uncertain real-world environments, we argue for the implementation of human cognitive biases in learning algorithms. We use insights from cognitive science and apply them to the AI field, combining theoretical considerations with tangible examples depicting promising bias implementation scenarios. Ultimately, this paper is the first tentative step to explicitly putting the idea forth to implement cognitive biases into machines.
Integrity signals
Registry
Cites
Statistics
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?
Research in machine psychology suggests that human and AI decision-making can differ considerably.
“At the same time, research in machine psychology, a nascent foundational interdisciplinary field that seeks to explain how AI systems process information and make decisions, suggests that human and AI decision-making can differ considerably (Hagendorff 2023).”
From Machine marketing: rethinking the customer in the age of generative AI (2026) · cites this paper as Hagendorff 2023
Machine psychology would examine how AI customers perceive, decide, act, and interact in ways that resemble human behavior, rather than interpreting the internal representations and design components of the neural networks underlying LLMs.
“Researchers have proposed that such an endeavor necessitates the establishment of an academic area of machine psychology (Hagendorff, 2023), with important implications for the marketing discipline.”
From Machine marketing: rethinking the customer in the age of generative AI (2026) · cites this paper as Hagendorff, 2023
Researchers have discussed deliberately implementing human-like cognitive biases in AI systems to more closely mirror human decision-making.
“Researchers have even discussed deliberately implementing human-like cognitive biases in AI systems to more closely mirror human decision-making (Besta et al. 2025;Hagendorff and Fabi 2023).”
From Machine marketing: rethinking the customer in the age of generative AI (2026) · cites this paper as Hagendorff and Fabi 2023
Cites
Tversky, A., & Kahneman, D. (1974) · Science · doi:10.1126/science.185.4157.1124 · Cited by 28,810 · cited 2× · see citing works
“…and inductive biases represent biases in machine learning systems, cognitive biases stand for human biases that are scrutinised with means of psychology and that can be due to intelligence limitations, motivational factors, and adaptations to situational circumstance (Tversky & Kahneman, 1974).”
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 1× · see citing works
“Biases are a “natural” part of large text corpora and hence large language models (Bender et al. 2021).”
Shortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224 · see citing works
Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., & Oermann, E. K. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002683 · Cited by 1,719 · see citing works
Deep Learning: A Critical Appraisal
Marcus, G. (2018) · arXiv · doi:10.48550/arxiv.1801.00631 · Cited by 853 · see citing works
Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries
Olteanu, A., Castillo, C., Diaz, F., & Kıcıman, E. (2019) · Frontiers in Big Data · doi:10.3389/fdata.2019.00013 · Cited by 763 · cited 1× · see citing works
“First, data bias is a systematic distortion in the sampled data that can be caused by selection processes of data sources, the way in which data from these sources are acquired, as well as by processing operations such as cleaning or aggregation (Olteanu et al., 2019).”
Algorithmic Bias in Autonomous Systems
Danks, D., & London, A. J. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/654 · Cited by 472 · see citing works
Schaffer, C. (1993) · Machine Learning · doi:10.1023/a:1022653209073 · Cited by 310 · see citing works
Adaptive rationality: an evolutionary perspective on cognitive bias
Haselton, M. G., Bryant, G. A., Wilke, A., Frederick, D. A., Galperin, A., Frankenhuis, W. E., & Moore, T. (2009) · Social Cognition · doi:10.1521/soco.2009.27.5.733 · Cited by 222 · cited 1× · see citing works
“According to the theory of ecological rationality (Gigerenzer & Gaissmaier, 2011; Gigerenzer, 1991, 1996; Haselton et al., 2009; Vranas, 2000), only under conditions of a mismatch between current environments and evolutionary acquired adaptations, for instance, in artificial laboratory settings,…”
Hagendorff, T. (2021) · Minds and Machines · doi:10.1007/s11023-021-09573-8 · Cited by 47 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Abramski, K., Citraro, S., Lombardi, L., Rossetti, G., & Stella, M. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7030124 · Cited by 81 · see citing works
Machine marketing: rethinking the customer in the age of generative AI
Sarstedt, M., Adler, S. J., & Imschloss, M. (2026) · Journal of Marketing Analytics · doi:10.1057/s41270-026-00521-y · Cited by 3 · see citing works
- Authors
- Hagendorff, T., & Fabi, S.
- Affiliations
- University of Tübingen (DE)
- University of California San Diego (US)
- Corresponding author
- Hagendorff, Thilo
- Venue
- Journal of Experimental & Theoretical Artificial Intelligence
- Publisher
- Informa UK Limited
- Published
- 2023-02-13
- Volume
- 36
- Issue
- 8
- Pages
- 1885-1898
- ISSN
- 0952-813X (ISSN-L)
- 1362-3079
- OpenAlex
- W4320734175
- Cited by
- 20
- References
- 10
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 4 · 2023: 2
- FWCI
- 1.77
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Locations
- Journal of Experimental & Theoretical Artificial Intelligence (publishedVersion)
- Universitätsbibliothek Tübingen
- Funders
- Deutsche Forschungsgemeinschaft (390727645)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Social Sciences › Decision Sciences › General Decision Sciences › Decision-Making and Behavioral Economics
- Keywords
- cognitive biases, algorithmic decision-making, uncertainty, learning algorithms
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
