Synthetic Data-Driven Prompt Tuning for Financial QA over Tables and Documents
By: Yaoning Yu , Kaimin Chang , Ye Yu and more
Potential Business Impact:
Helps computers understand money reports better.
Financial documents like earning reports or balance sheets often involve long tables and multi-page reports. Large language models have become a new tool to help numerical reasoning and understanding these documents. However, prompt quality can have a major effect on how well LLMs perform these financial reasoning tasks. Most current methods tune prompts on fixed datasets of financial text or tabular data, which limits their ability to adapt to new question types or document structures, or they involve costly and manually labeled/curated dataset to help build the prompts. We introduce a self-improving prompt framework driven by data-augmented optimization. In this closed-loop process, we generate synthetic financial tables and document excerpts, verify their correctness and robustness, and then update the prompt based on the results. Specifically, our framework combines a synthetic data generator with verifiers and a prompt optimizer, where the generator produces new examples that exposes weaknesses in the current prompt, the verifiers check the validity and robustness of the produced examples, and the optimizer incrementally refines the prompt in response. By iterating these steps in a feedback cycle, our method steadily improves prompt accuracy on financial reasoning tasks without needing external labels. Evaluation on DocMath-Eval benchmark demonstrates that our system achieves higher performance in both accuracy and robustness than standard prompt methods, underscoring the value of incorporating synthetic data generation into prompt learning for financial applications.
Similar Papers
Synthetic Clarification and Correction Dialogues about Data-Centric Tasks -- A Teacher-Student Approach
Computation and Language
AI learns to ask questions and fix mistakes.
The Art of Asking: Multilingual Prompt Optimization for Synthetic Data
Computation and Language
Makes AI understand many languages better.
Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails
Computation and Language
Creates safer AI by spotting bad health advice.