A Modular Agent-Based Approach to Complex Data Question-Answering with SQL Generation and Parameter-Efficient Fine-Tuning
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".