# LLM-driven Imitation of Subrational Behavior : Illusion or Reality?

arXiv: https://arxiv.org/abs/2402.08755 · HTML: https://mlsanity.com/paper/2402.08755/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 80 references that are in the map.
- First posted on arXiv 13 Feb 2024.

## Builds on (most cited first, 30 of 36)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [Model-Based Imitation Learning for Urban Driving](https://mlsanity.com/paper/2210.07729/) (2022)
- [Towards artificial general intelligence via a multimodal foundation model](https://mlsanity.com/paper/2110.14378/) (2021)
- [Epidemic Modeling with Generative Agents](https://mlsanity.com/paper/2307.04986/) (2023)
- [Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior](https://mlsanity.com/paper/1805.08010/) (2018)
- [Large Language Models and the Reverse Turing Test](https://mlsanity.com/paper/2207.14382/) (2022)
- [Learning to simulate realistic limit order book markets from data as a World Agent](https://mlsanity.com/paper/2210.09897/) (2022)

## Built on by (most cited first, 12 of 12)

- [Large Language Models Assume People are More Rational than We Really are](https://mlsanity.com/paper/2406.17055/) (2024)
- [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024)
- [The Effect of State Representation on LLM Agent Behavior in Dynamic Routing Games](https://mlsanity.com/paper/2506.15624/) (2025)
- [Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System](https://mlsanity.com/paper/2508.10043/) (2025)
- [Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems](https://mlsanity.com/paper/2405.13362/) (2024)
- [Chat Bankman-Fried: an Exploration of LLM Alignment in Finance](https://mlsanity.com/paper/2411.11853/) (2024)
- [Profile-Aware Maneuvering: A Dynamic Multi-Agent System for Robust GAIA Problem Solving by AWorld](https://mlsanity.com/paper/2508.09889/) (2025)
- [BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation](https://mlsanity.com/paper/2405.17039/) (2024)
- [LLM Agents Display Human Biases but Exhibit Distinct Learning Patterns](https://mlsanity.com/paper/2503.10248/) (2025)
- [Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets](https://mlsanity.com/paper/2609.29509/) (2026)
- [MultiSurf-GPT: Facilitating Context-Aware Reasoning with Large-Scale Language Models for Multimodal Surface Sensing](https://mlsanity.com/paper/2408.07311/) (2024)
- [The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance](https://mlsanity.com/paper/2610.06673/) (2026)

## Abstract (arXiv)

Modeling subrational agents, such as humans or economic households, is inherently challenging due to the difficulty in calibrating reinforcement learning models or collecting data that involves human subjects. Existing work highlights the ability of Large Language Models (LLMs) to address complex reasoning tasks and mimic human communication, while simulation using LLMs as agents shows emergent social behaviors, potentially improving our comprehension of human conduct. In this paper, we propose to investigate the use of LLMs to generate synthetic human demonstrations, which are then used to learn subrational agent policies though Imitation Learning. We make an assumption that LLMs can be used as implicit computational models of humans, and propose a framework to use synthetic demonstrations derived from LLMs to model subrational behaviors that are characteristic of humans (e.g., myopic behavior or preference for risk aversion). We experimentally evaluate the ability of our framework to model sub-rationality through four simple scenarios, including the well-researched ultimatum game and marshmallow experiment. To gain confidence in our framework, we are able to replicate well-established findings from prior human studies associated with the above scenarios. We conclude by discussing the potential benefits, challenges and limitations of our framework.