InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior

2025-07-09

AI Summary

In behavioral finance research, aligning large language models (LLMs) with investor decision-making under herding behavior is hindered by the scarcity of real-world user data, impeding effective supervised fine-tuning (SFT). To address this, we propose InvestAlign—a novel paradigm that bypasses reliance on sensitive real-user data by generating high-quality, interpretable theoretical solutions as SFT supervision signals, grounded in optimal investment theory. This approach ensures privacy preservation while enhancing generalizability. The framework integrates theoretical modeling, SFT, and LLM agent techniques to instantiate InvestAgent, an intelligent investment agent. Experiments demonstrate that InvestAlign significantly accelerates model convergence and achieves superior fidelity in replicating real investor behavior—both in simple and complex investment tasks—outperforming prior data-driven methods. To our knowledge, this is the first work to realize theory-driven behavioral finance alignment for LLMs.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Behavioral Game Theory

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Aligning Large Language Models (LLMs) with investor decision-making processes under herd behavior is a critical challenge in behavioral finance, which grapples with a fundamental limitation: the scarcity of real-user data needed for Supervised Fine-Tuning (SFT). While SFT can bridge the gap between LLM outputs and human behavioral patterns, its reliance on massive authentic data imposes substantial collection costs and privacy risks. We propose InvestAlign, a novel framework that constructs high-quality SFT datasets by leveraging theoretical solutions to similar and simple optimal investment problems rather than complex scenarios. Our theoretical analysis demonstrates that training LLMs with InvestAlign-generated data achieves faster parameter convergence than using real-user data, suggesting superior learning efficiency. Furthermore, we develop InvestAgent, an LLM agent fine-tuned with InvestAlign, which demonstrates significantly closer alignment to real-user data than pre-SFT models in both simple and complex investment problems. This highlights our proposed InvestAlign as a promising approach with the potential to address complex optimal investment problems and align LLMs with investor decision-making processes under herd behavior. Our code is publicly available at https://github.com/thu-social-network-research-group/InvestAlign.

Problem

• Aligning LLMs with investor decisions under herd behavior
• Overcoming data scarcity for supervised fine-tuning in finance
• Generating synthetic data to replace real-user investment data

Innovation

• Leverages theoretical solutions for SFT datasets
• Achieves faster parameter convergence than real data
• Fine-tunes LLM agent closer to real-user data