将图文分离转为图文融合，提升科学视觉问答跨语言性能
A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA
- 将图像与文本合成统一图像输入，构建新数据格式
- 在13种语言上实现显著性能提升，跨语言迁移效果好
- 仅用小模型+少量合成数据，即可获得强零样本泛化能力
科学视觉问答因科学图表的复杂性及多模态上下文而极具挑战。传统方法将图像与文本（如问题和选项）视为独立输入。EXAMS-V提出新范式，将视觉与文本内容嵌入单一图像。然而，即使最先进的专有模型在零样本设置下表现仍不佳，凸显了任务特定微调的必要性。为解决该‘图文融合’格式下的训练数据稀缺问题，我们通过转换现有分离的图像-文本对，生成新的合成数据集。在混合合成数据与EXAMS-V数据上微调一个小型多语言多模态模型，在13种语言上均取得显著提升，验证了良好的平均性能增益与跨语言迁移能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。