AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

GridVQA-X: A Diagnostic Framework for Evaluating Multimodal Explainability Methods

Sujay Belsare, Sushant Kumar, Sudarshan Nikhil, Ponnurangam Kumaraguru, Chirag Agarwal

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Benchmarks and analysis of MLLMs · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on D_spur (shortcut-injected data) instead of D_pureMDETR · GridVQA D_pure evaluationaccuracy: 1.000 -> 49%Hurt
evaluate M_spur on Depth-2 Mixed instead of Depth-1 attribute-only queriesM_spur · GridVQA D_pureaccuracy: 100% -> 8%Hurt
increase query depth from 2 to 3 for M_spur on Mixed queriesM_spur · GridVQA D_pure Mixedaccuracy: 8% -> 14%Mixed
increase query depth from 1 to 3 for EMAP on Mixed Form 0EMAP · GridVQA D_pure Mixed Form 0interaction fraction: 0.821 -> 0.673Hurt
increase query depth from 1 to 3 for InterSHAP on MixedInterSHAP · GridVQA D_pure Mixedinteraction score: 0.921 -> 0.629Hurt
switch task from Existence to Counting for InterSHAPInterSHAP · GridVQA-Xinteraction score: 0.742 -> 0.921Mixed
explain M_spur instead of M_pure with MultiSHAPMultiSHAP · GridVQA-XRMA: 0.616 -> 0.689Mixed
explain M_spur instead of M_pure with MultiVizMultiViz · GridVQA-XRMA: approx 0.44 for bothNo clear effect
add adversarial distractors in D_pure rather than shortcut-consistent distractors (ablation)Case-1 bag-of-words heuristic · GridVQAshortcut success rate: 100% -> 36.07%Hurt
add confuser-region distractors (Theorem 1) for dense depth-2 Mixed queries (ablation)Partial logic heuristic · GridVQA D2_M_F0_d0.7predictive ratio: 16.40% and 16.87%Hurt
add target-boost/suppress balancing to dataset generation (ablation)Majority-class heuristic · GridVQA bucketsheuristic success rate: approx 44%Hurt
increase density from d0.3 to d0.7 for M_spur on Depth-3 Mixed Form 0M_spur · GridVQA D_pure Mixed D3 Form 0accuracy: 14 -> 0Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy