{"total":18,"rows":[{"id":"2312.17174","title":"Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution","created":"2023-12-28","cited_by_count":34,"area":"mllm"},{"id":"2408.02001","title":"AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis","created":"2024-08-04","cited_by_count":12,"area":"mllm"},{"id":"2510.00047","title":"Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations","created":"2025-09-27","cited_by_count":12,"area":"mllm"},{"id":"2504.05445","title":"Probing the Visualization Literacy of Vision Language Models: the Good, the Bad, and the Ugly","created":"2025-04-07","cited_by_count":11,"area":"mllm"},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2509.22415","title":"Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models","created":"2025-09-26","cited_by_count":5,"area":"mllm"},{"id":"2606.17710","title":"Vision-language models for chest radiography do not always need the image","created":"2026-06-16","cited_by_count":2,"area":"mllm"},{"id":"2509.15243","title":"Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models","created":"2025-09-17","cited_by_count":1,"area":"mllm"},{"id":"2604.17126","title":"Prompt Sensitivity in Vision-Language Grounding: How Small Changes in Wording Affect Object Detection","created":"2026-04-18","cited_by_count":1,"area":"mllm"},{"id":"2607.18577","title":"Attention Without Grounding: Causal Evaluation of Visual Explanations in Medical VLMs","created":"2026-07-20","cited_by_count":1,"area":"mllm"},{"id":"2509.21102","title":"Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models","created":"2025-09-25","cited_by_count":0,"area":"mllm"},{"id":"2608.24430","title":"Vision Language Model Fusion for Explainable Face Recognition","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2609.05889","title":"Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimization","created":"2026-09-05","cited_by_count":0,"area":"mllm"},{"id":"2609.13308","title":"GroundBench: A Factorized, Counterfactual Benchmark for Locating VLM Affordance Failures","created":"2026-09-10","cited_by_count":0,"area":"mllm"},{"id":"2609.17953","title":"EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing","created":"2026-09-16","cited_by_count":0,"area":"mllm"},{"id":"2609.21879","title":"Benchmarking the Explanatory Quality of Open-Weight Vision-Language Models in Face Recognition","created":"2026-09-18","cited_by_count":0,"area":"mllm"},{"id":"2609.30210","title":"The Alignment Illusion in Multimodal Large Language Models","created":"2026-09-24","cited_by_count":0,"area":"mllm"},{"id":"2610.15129","title":"GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning?","created":"2026-10-10","cited_by_count":0,"area":"mllm"}],"next_cursor":null}