Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations

TL;DR

This paper improves financial chart interpretation by fine-tuning a module to convert chart images into structured tables, which enhances large language models' reasoning accuracy in visual data analysis.

Contribution

It introduces a fine-tuned DEPLOT module for converting chart images into structured tables, boosting reasoning performance of LLMs in financial visual data tasks.

Findings

Structured tables improve LLM reasoning accuracy.

Fine-tuned DEPLOT outperforms base version in mapping similarity.

Enhanced reasoning demonstrated on curated chart-question pairs.

Abstract

Chart interpretation is crucial for visual data analysis, but accurately extracting information from charts poses significant challenges for automated models. This study investigates the fine-tuning of DEPLOT, a modality conversion module that translates the image of a plot or chart to a linearized table, on a custom dataset of 50,000 bar charts. The dataset comprises simple, stacked, and grouped bar charts, targeting the unique structural features of these visualizations. The finetuned DEPLOT model is evaluated against its base version using a test set of 1,000 images and two metrics: Relative Mapping Similarity (RMS), which measures categorical mapping accuracy, and Relative Number Set Similarity (RNSS), which evaluates numerical interpretation accuracy. To further explore the reasoning capabilities of large language models (LLMs), we curate an additional set of 100 bar chart images paired with question answer sets. Our findings demonstrate that providing a structured intermediate table alongside the image significantly enhances LLM reasoning performance compared to direct image queries.