# A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA

Source: [A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA](<https://www.sota2.com/research/paper/68fa7b931e209131cea8937c>)

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

Data updated: 2025-10-26T05:43:27.824Z

Authors: Belal Shoer, Yova Kementchedjhieva

Published: 2025-09-24T13:41:04.000Z

## Abstract

Scientific visual question answering poses significant challenges for vision-language models due to the complexity of scientific figures and their multimodal context. Traditional approaches treat the figure and accompanying text (e.g., questions and answer options) as separate inputs. EXAMS-V introduced a new paradigm by embedding both visual and textual content into a single image. However, even state-of-the-art proprietary models perform poorly on this setup in zero-shot settings, underscoring the need for task-specific fine-tuning. To address the scarcity of training data in this "text-in-image" format, we synthesize a new dataset by converting existing separate image-text pairs into unified images. Fine-tuning a small multilingual multimodal model on a mix of our synthetic data and EXAMS-V yields notable gains across 13 languages, demonstrating strong average improvements and cross-lingual transfer.

## 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/2509.20119>)

[PDF](<https://arxiv.org/pdf/2509.20119.pdf>)
