Numerical Reasoning for Financial Reports
This addresses the challenge of swift decision-making in dynamic markets for financial analysts by providing an incremental improvement in automated report analysis.
The paper tackled the problem of extracting key indicators from lengthy financial reports by fine-tuning Large Language Models (LLMs) like Llama-2 7B and T5 on the FinQA dataset for question answering, achieving results comparable to baseline accuracy in numerical reasoning and calculation.
Financial reports offer critical insights into a company's operations, yet their extensive length typically spanning 30 40 pages poses challenges for swift decision making in dynamic markets. To address this, we leveraged finetuned Large Language Models (LLMs) to distill key indicators and operational metrics from these reports basis questions from the user. We devised a method to locate critical data, and leverage the FinQA dataset to fine-tune both Llama-2 7B and T5 models for customized question answering. We achieved results comparable to baseline on the final numerical answer, a competitive accuracy in numerical reasoning and calculation.