Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior
Preprint
Abstract
Human decision-making belongs to the foundation of our society and civilization, but we are on the verge of a future where much of it will be delegated to artificial intelligence. The arrival of Large Language Models (LLMs) has transformed the nature and scope of AI-supported decision-making; however, the process by which they learn to make decisions, compared to humans, remains poorly understood. In this study, we examined the decision-making behavior of five leading LLMs across three core dimensions of real-world decision-making: uncertainty, risk, and set-shifting. Using three well-established experimental psychology tasks designed to probe these dimensions, we benchmarked LLMs against 360 newly recruited human participants. Across all tasks, LLMs often outperformed humans, approaching near-optimal performance. Moreover, the processes underlying their decisions diverged fundamentally from those of humans. On the one hand, our finding demonstrates the ability of LLMs to manage uncertainty, calibrate risk, and adapt to changes. On the other hand, this disparity highlights the risks of relying on them as substitutes for human judgment, calling for further inquiry.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- Large language models present new questions for decision supportInternational Journal of Information Management, 2024
- Exploring decision-making performance in young adults with mental health disorders: a comparative study using the Cambridge gambling taskPsychological Medicine, 2024
- A computational model of the Cambridge gambling task with applications to substance use disordersDrug and Alcohol Dependence, 2020
- oTree—An open-source platform for laboratory, online, and field experimentsJournal of Behavioral and Experimental Finance, 2016
- Sequential learning models for the Wisconsin card sort task: Assessing processes in substance dependent individualsJournal of Mathematical Psychology, 2010
- Finite-time Analysis of the Multiarmed Bandit ProblemMachine Learning, 2002
- Dissociable Deficits in the Decision-Making Cognition of Chronic Amphetamine Abusers, Opiate Abusers, Patients with Focal Damage to Prefrontal Cortex, and Tryptophan-Depleted Normal Volunteers Evidence for Monoaminergic MechanismsNeuropsychopharmacology, 1999
- Insensitivity to future consequences following damage to human prefrontal cortexCognition, 1994
- Dynamic decision making: Human control of complex systemsActa Psychologica, 1992
- Recent developments in modeling preferences: Uncertainty and ambiguityJournal of Risk and Uncertainty, 1992