Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Wei, Dhanda, Amit, Chen, Daniel L., Hansen, Christian B.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912963999301632
author Lu, Wei
Dhanda, Amit
Chen, Daniel L.
Hansen, Christian B.
author_facet Lu, Wei
Dhanda, Amit
Chen, Daniel L.
Hansen, Christian B.
contents As large language models (LLMs) increasingly act as autonomous agents in markets and organizations, their behavior in strategic environments becomes economically consequential. We document that off-the-shelf LLM agents exhibit systematic deviations from payoff-sensitive behavior in canonical economic games, including excessive cooperation and limited responsiveness to incentives. We introduce a supervised fine-tuning approach that aligns agent behavior with explicit economic preferences. Specifically, we generate optimal strategies under two stylized utility specifications, homo economicus, which maximizes self-interest, and homo moralis, which incorporates Kantian universalizability, and use these utility-implied reasoning and strategies to guide fine-tuning. Fine-tuning on a small, theory-driven synthetic dataset induces persistent and interpretable shifts in strategic behavior. In applications to moral dilemmas and repeated duopoly pricing, agents aligned to different preference structures produce systematically distinct equilibrium outcomes and pricing dynamics. These results frame AI alignment in multi-agent settings as an objective-design problem and illustrate how economic theory can guide the design of strategically coherent AI agents.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20796
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach
Lu, Wei
Dhanda, Amit
Chen, Daniel L.
Hansen, Christian B.
General Economics
Economics
Artificial Intelligence
Machine Learning
As large language models (LLMs) increasingly act as autonomous agents in markets and organizations, their behavior in strategic environments becomes economically consequential. We document that off-the-shelf LLM agents exhibit systematic deviations from payoff-sensitive behavior in canonical economic games, including excessive cooperation and limited responsiveness to incentives. We introduce a supervised fine-tuning approach that aligns agent behavior with explicit economic preferences. Specifically, we generate optimal strategies under two stylized utility specifications, homo economicus, which maximizes self-interest, and homo moralis, which incorporates Kantian universalizability, and use these utility-implied reasoning and strategies to guide fine-tuning. Fine-tuning on a small, theory-driven synthetic dataset induces persistent and interpretable shifts in strategic behavior. In applications to moral dilemmas and repeated duopoly pricing, agents aligned to different preference structures produce systematically distinct equilibrium outcomes and pricing dynamics. These results frame AI alignment in multi-agent settings as an objective-design problem and illustrate how economic theory can guide the design of strategically coherent AI agents.
title Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach
topic General Economics
Economics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.20796