# XBench: A Comprehensive Benchmark for Visual-Language Explanations in Chest Radiography

arXiv: https://arxiv.org/abs/2510.19599 · HTML: https://mlsanity.com/paper/2510.19599/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations](https://mlsanity.com/paper/2012.15029/) (2020)
- [MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology](https://mlsanity.com/paper/2301.02228/) (2023)
- [Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images](https://mlsanity.com/paper/2302.14042/) (2023)
- [CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification](https://mlsanity.com/paper/2402.17417/) (2024)
- [ChestX-Det10: Chest X-ray Dataset on Detection of Thoracic Abnormalities](https://mlsanity.com/paper/2006.10550/) (2020)
- [Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework](https://mlsanity.com/paper/2403.07636/) (2024)
- [DeViDe: Faceted medical knowledge for improved medical vision-language pre-training](https://mlsanity.com/paper/2404.03618/) (2024)
- [BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays](https://mlsanity.com/paper/2410.21969/) (2024)
- [DWARF: Disease-weighted network for attention map refinement](https://mlsanity.com/paper/2406.17032/) (2024)

## Built on by (most cited first, 3 of 3)

- [RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding](https://mlsanity.com/paper/2608.00147/) (2026)
- [Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models](https://mlsanity.com/paper/2610.02270/) (2026)
- [AgroGround: Multi-Granularity Grounded Recognition in Agriculture](https://mlsanity.com/paper/2610.04425/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) have recently shown remarkable zero-shot performance in medical image understanding, yet their grounding ability, the extent to which textual concepts align with visual evidence, remains underexplored. In the medical domain, however, reliable grounding is essential for interpretability and clinical adoption. In this work, we present the first systematic benchmark for evaluating cross-modal interpretability in chest X-rays across seven CLIP-style VLM variants. We generate visual explanations using cross-attention and similarity-based localization maps, and quantitatively assess their alignment with radiologist-annotated regions across multiple pathologies. Our analysis reveals that: (1) while all VLM variants demonstrate reasonable localization for large and well-defined pathologies, their performance substantially degrades for small or diffuse lesions; (2) models that are pretrained on chest X-ray-specific datasets exhibit improved alignment compared to those trained on general-domain data. (3) The overall recognition ability and grounding ability of the model are strongly correlated. These findings underscore that current VLMs, despite their strong recognition ability, still fall short in clinically reliable grounding, highlighting the need for targeted interpretability benchmarks before deployment in medical practice. XBench code is available at https://github.com/Roypic/Benchmarkingattention