{"ID":2854679,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14741","arxiv_id":"2510.14741","title":"DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models","abstract":"Understanding and explaining the behavior of machine learning models is essential for building transparent and trustworthy AI systems. We introduce DEXTER, a data-free framework that employs diffusion models and large language models to generate global, textual explanations of visual classifiers. DEXTER operates by optimizing text prompts to synthesize class-conditional images that strongly activate a target classifier. These synthetic samples are then used to elicit detailed natural language reports that describe class-specific decision patterns and biases. Unlike prior work, DEXTER enables natural language explanation about a classifier's decision process without access to training data or ground-truth labels. We demonstrate DEXTER's flexibility across three tasks-activation maximization, slice discovery and debiasing, and bias explanation-each illustrating its ability to uncover the internal mechanisms of visual classifiers. Quantitative and qualitative evaluations, including a user study, show that DEXTER produces accurate, interpretable outputs. Experiments on ImageNet, Waterbirds, CelebA, and FairFaces confirm that DEXTER outperforms existing approaches in global model explanation and class-level bias reporting. Code is available at https://github.com/perceivelab/dexter.","short_abstract":"Understanding and explaining the behavior of machine learning models is essential for building transparent and trustworthy AI systems. We introduce DEXTER, a data-free framework that employs diffusion models and large language models to generate global, textual explanations of visual classifiers. DEXTER operates by opt...","url_abs":"https://arxiv.org/abs/2510.14741","url_pdf":"https://arxiv.org/pdf/2510.14741v2","authors":"[\"Simone Carnemolla\",\"Matteo Pennisi\",\"Sarinda Samarasinghe\",\"Giovanni Bellitto\",\"Simone Palazzo\",\"Daniela Giordano\",\"Mubarak Shah\",\"Concetto Spampinato\"]","published":"2025-10-16T14:43:25Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":608183,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2854679,"paper_url":"https://arxiv.org/abs/2510.14741","paper_title":"DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models","repo_url":"https://github.com/perceivelab/dexter","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}