# Numerical Reasoning for Financial Reports

Source: [Numerical Reasoning for Financial Reports](<https://www.sota2.com/research/paper/68fa71a91e209131cea5263e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:03.414Z

Authors: Abhinav Arun, Ashish Dhiman, Mehul Soni, Yibei Hu

Published: 2023-12-22T17:46:36.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.14870>)

[PDF](<https://arxiv.org/pdf/2312.14870.pdf>)
