# On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

arXiv: https://arxiv.org/abs/2002.10215 · HTML: https://mlsanity.com/paper/2002.10215/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2020.

## Built on by (most cited first, 30 of 78)

- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning](https://mlsanity.com/paper/2110.13214/) (2021)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text](https://mlsanity.com/paper/2105.05486/) (2021)
- [VisualMRC: Machine Reading Comprehension on Document Images](https://mlsanity.com/paper/2101.11272/) (2021)
- [BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions](https://mlsanity.com/paper/2308.09936/) (2023)
- [NVLM: Open Frontier-Class Multimodal LLMs](https://mlsanity.com/paper/2409.11402/) (2024)
- [Hierarchical multimodal transformers for Multi-Page DocVQA](https://mlsanity.com/paper/2212.05935/) (2022)
- [Medical Visual Question Answering: A Survey](https://mlsanity.com/paper/2111.10056/) (2021)
- [MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer](https://mlsanity.com/paper/2401.10208/) (2024)
- [LaTr: Layout-Aware Transformer for Scene-Text VQA](https://mlsanity.com/paper/2112.12494/) (2021)
- [OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text](https://mlsanity.com/paper/2406.08418/) (2024)
- [Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding](https://mlsanity.com/paper/2203.15442/) (2022)
- [FineVision: Open Data Is All You Need](https://mlsanity.com/paper/2510.17269/) (2025)
- [EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering](https://mlsanity.com/paper/2502.07411/) (2025)
- [TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens](https://mlsanity.com/paper/2410.05261/) (2024)
- [One RL to See Them All: Visual Triple Unified Reinforcement Learning](https://mlsanity.com/paper/2505.18129/) (2025)
- [PDFVQA: A New Dataset for Real-World VQA on PDF Documents](https://mlsanity.com/paper/2304.06447/) (2023)
- [LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding](https://mlsanity.com/paper/2605.27365/) (2026)
- [PreSTU: Pre-Training for Scene-Text Understanding](https://mlsanity.com/paper/2209.05534/) (2022)
- [PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models](https://mlsanity.com/paper/2412.09613/) (2024)
- [The Evolution of Multimodal Model Architectures](https://mlsanity.com/paper/2405.17927/) (2024)
- [Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning](https://mlsanity.com/paper/2103.05187/) (2021)
- [Watching the News: Towards VideoQA Models that can Read](https://mlsanity.com/paper/2211.05588/) (2022)
- [Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding](https://mlsanity.com/paper/2503.14140/) (2025)
- [Are Large Vision Language Models Good Game Players?](https://mlsanity.com/paper/2503.02358/) (2025)
- [ModaVerse: Efficiently Transforming Modalities with LLMs](https://mlsanity.com/paper/2401.06395/) (2024)

## Abstract (arXiv)

Visual Question Answering (VQA) methods have made incredible progress, but suffer from a failure to generalize. This is visible in the fact that they are vulnerable to learning coincidental correlations in the data rather than deeper relations between image content and ideas expressed in language. We present a dataset that takes a step towards addressing this problem in that it contains questions expressed in two languages, and an evaluation process that co-opts a well understood image-based metric to reflect the method's ability to reason. Measuring reasoning directly encourages generalization by penalizing answers that are coincidentally correct. The dataset reflects the scene-text version of the VQA problem, and the reasoning evaluation can be seen as a text-based version of a referring expression challenge. Experiments and analysis are provided that show the value of the dataset.