A Modular Agent-Based Approach to Complex Data Question-Answering with SQL Generation and Parameter-Efficient Fine-Tuning

This paper introduces an agent-based intelligent question-answering (QA) system designed for financial data queries, leveraging the power of the Tongyi Finance-14B large pretrained language model. By combining fine-tuning for both classification and generation tasks, and incorporating a modular agent framework for dynamic task management, the proposed system addresses the challenges of complex multi-table data queries. The system integrates Low-Rank Adaptation (LoRA) to optimize parameter learning and includes a robust SQL generation module. The multi-step reasoning process improves accuracy in intent recognition, data querying, and text comprehension. Additionally, an agent-driven task assignment mechanism enhances flexibility and generalization capabilities. Experimental results demonstrate that the system significantly outperforms traditional models, showcasing superior performance in key evaluation metrics. This work contributes to the advancement of intelligent QA systems for financial data, with future directions exploring its adaptability to more complex tasks and real-world applications.