Calibrating Behavioral Parameters with Large Language Models

Behavioral parameters such as loss aversion, herding, and extrapolation are central to asset pricing models but remain difficult to measure reliably. We develop a framework that treats large language models (LLMs) as calibrated measurement instruments for behavioral parameters. Using four models and 24{,}000 agent--scenario pairs, we document systematic rationality bias in baseline LLM behavior, including attenuated loss aversion, weak herding, and near-zero disposition effects relative to human benchmarks. Profile-based calibration induces large, stable, and theoretically coherent shifts in several parameters, with calibrated loss aversion, herding, extrapolation, and anchoring reaching or exceeding benchmark magnitudes. To assess external validity, we embed calibrated parameters in an agent-based asset pricing model, where calibrated extrapolation generates short-horizon momentum and long-horizon reversal patterns consistent with empirical evidence. Our results establish measurement ranges, calibration functions, and explicit boundaries for eight canonical behavioral biases.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-02-01

• Fields of study

  Computer Science, Economics

• Identifiers
  arXiv 2602.01022
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Using GPT for Market Research

  2024cited by this paper
• Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?

  2023cited by this paper
• Generative Agents: Interactive Simulacra of Human Behavior

  2023cited by this paper
• Out of One, Many: Using Language Models to Simulate Human Samples

  2022cited by this paper
• Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies

  2022cited by this paper
• Extrapolation and bubbles

  2018cited by this paper
• Expectations of Returns and Expected Returns

  2014influential reference
• Thirty Years of Prospect Theory in Economics: A Review and Assessment

  2012cited by this paper
• The Promise and Success of Lab-Field Generalizability in Experimental Economics: A Critical Reply to Levitt and List

  2011cited by this paper
• Structural vs. atheoretic approaches to econometrics

  2010cited by this paper
• Individual Risk Attitudes: Measurement, Determinants and Behavioral Consequences

  2009cited by this paper
• The trouble with overconfidence.

  2008cited by this paper
• Stocks as Lotteries: the Implications of Probability Weighting for Security Prices

  2008cited by this paper
• You have printed the following article : A Theory of Fads , Fashion , Custom , and Cultural Change as Informational Cascades

  2007cited by this paper
• The Boundaries of Loss Aversion

  2005cited by this paper
• Distinguishing Informational Cascades from Herd Behavior in the Laboratory

  2004cited by this paper
• Predicting the Next Step of a Random Walk: Experimental Evidence of Regime-Shifting Beliefs

  2002cited by this paper
• Risk Aversion and Incentive Effects

  2002cited by this paper
• Empirical regularities from interacting long- and short-memory investors in an agent-based stock market

  2001cited by this paper
• Overcoming the Inevitable Anchoring Effect: Considering the Opposite Compensates for Selective Accessibility

  2000cited by this paper
• Investor Psychology and Security Market Under- and Overreactions

  1999influential reference
• Scaling and criticality in a stochastic multi-agent model of a financial market

  1999cited by this paper
• Heterogeneous beliefs and routes to chaos in a simple asset pricing model

  1998cited by this paper
• Information Cascades in the Laboratory

  1998cited by this paper
• A Model of Investor Sentiment

  1997cited by this paper
• Are Investors Reluctant to Realize Their Losses

  1996cited by this paper
• Contrarian Investment, Extrapolation, and Risk

  1994cited by this paper
• Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency

  1993influential reference
• Advances in prospect theory: Cumulative representation of uncertainty

  1992influential reference
• The Disposition Effect in Securities Trading: An Experimental Analysis

  1991cited by this paper
• Experimental Tests of the Endowment Effect and the Coase Theorem

  1990cited by this paper
• POST-EARNINGS-ANNOUNCEMENT DRIFT - DELAYED PRICE RESPONSE OR RISK PREMIUM

  1989cited by this paper
• Experts, amateurs, and real estate: An anchoring-and-adjustment perspective on property pricing decisions

  1987cited by this paper
• The Disposition to Sell Winners Too Early and Ride Losers Too Long: Theory and Evidence: Discussion

  1985influential reference
• Judgment Under Uncertainty: Heuristics and Biases.

  1984influential reference
• You have printed the following article : Prospect Theory : An Analysis of Decision under Risk

  year unknowninfluential reference

• No citing papers are available for this paper.