mlsanityData to 14 Oct 2026

A Novel Framework for Automated Explain Vision Model Using Vision-Language Models

arXiv 2508.20227 ↗First posted 27 Aug 2025cs.CV cs.AI cs.CLcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

The development of many vision models mainly focuses on improving their performance using metrics such as accuracy, IoU, and mAP, with less attention to explainability due to the complexity of applying xAI methods to provide a meaningful explanation of trained models. Although many existing xAI methods aim to explain vision models sample-by-sample, methods explaining the general behavior of vision models, which can only be captured after running on a large dataset, are still underexplored. Furthermore, understanding the behavior of vision models on general images can be very important to prevent biased judgments and help identify the model's trends and patterns. With the application of Vision-Language Models, this paper proposes a pipeline to explain vision models at both the sample and dataset levels. The proposed pipeline can be used to discover failure cases and gain insights into vision models with minimal effort, thereby integrating vision model development with xAI analysis to advance image analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 2 of its 32 references that are in the map. First posted on arXiv 27 Aug 2025.

Builds on

2 of 32 references.

References · 2

  1. 2014Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNetcited by 60
  2. 2024LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Taskscited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Adapting Vision-Language Models for Human-Readable XAI in Industrial Object Detection
  2. 2026DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
  3. 2025A Survey on Interpretability in Visual Recognition
  4. 2024GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers
  5. 2024LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models
  6. 2023Interpreting and Controlling Vision Foundation Models via Text Explanations
  7. 2025PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
  8. 2024Benchmarking XAI Explanations with Human-Aligned Evaluations