用大模型测量行为金融参数，校准后能复现真实市场现象
Calibrating Behavioral Parameters with Large Language Models
- 把大模型当测量工具，通过场景配对校准行为参数
- 校准后损失厌恶、羊群效应等参数达人类基准水平
- 结果可直接用于模拟真实市场中的动量与反转规律
损失厌恶、羊群效应和外推倾向等行为参数是资产定价模型的核心，但难以可靠度量。本文提出一种框架，将大语言模型（LLMs）作为行为参数的校准测量工具。基于四个模型和24,000个代理-情景组合，我们发现基线大模型行为存在系统性理性偏差：损失厌恶减弱、羊群效应微弱、处置效应接近零，均低于人类基准。通过基于特征的校准，多个参数发生显著、稳定且理论自洽的改变，校准后的损失厌恶、羊群效应、外推和锚定效应均达到或超过人类基准水平。为验证外部有效性，我们将校准参数嵌入基于代理的资产定价模型，结果显示校准后的外推行为生成了短期动量与长期反转模式，符合实证证据。研究确立了八个经典行为偏差的测量范围、校准函数及明确边界。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。