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

TL;DR

InvestAlign introduces a novel framework that uses theoretical solutions to generate high-quality fine-tuning data, enabling LLMs to better mimic investor decision-making under herd behavior with less reliance on scarce real-user data.

Contribution

The paper presents InvestAlign, a new method for constructing effective training datasets using theoretical investment models, improving LLM alignment with investor behavior while reducing data collection costs.

Findings

InvestAlign-generated data leads to faster LLM training convergence.

InvestAgent fine-tuned with InvestAlign data aligns more closely with real-user decisions.

The approach effectively handles both simple and complex investment scenarios.

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.