FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation
This addresses the data scarcity and lack of evaluation metrics for equity research report generation, which is a domain-specific problem for financial analysts, and is incremental as it builds on existing LLM capabilities.
The authors tackled the problem of automating Equity Research Report generation by introducing FinRpt, a dataset and evaluation benchmark, and FinRpt-Gen, a multi-agent framework, resulting in strong performance as indicated by experimental results.
While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equity Research Report generation remains uncharted territory. In this paper, we formulate the Equity Research Report (ERR) Generation task for the first time. To address the data scarcity and the evaluation metrics absence, we present an open-source evaluation benchmark for ERR generation - FinRpt. We frame a Dataset Construction Pipeline that integrates 7 financial data types and produces a high-quality ERR dataset automatically, which could be used for model training and evaluation. We also introduce a comprehensive evaluation system including 11 metrics to assess the generated ERRs. Moreover, we propose a multi-agent framework specifically tailored to address this task, named FinRpt-Gen, and train several LLM-based agents on the proposed datasets using Supervised Fine-Tuning and Reinforcement Learning. Experimental results indicate the data quality and metrics effectiveness of the benchmark FinRpt and the strong performance of FinRpt-Gen, showcasing their potential to drive innovation in the ERR generation field. All code and datasets are publicly available.