EvQA

The 'EVQA' dataset/benchmark contains samples designed to evaluate the explainability and trustworthiness of Visual Question Answering (VQA) models by focusing on the generation of visual and textual rationales for predicted answers.

Papers using EvQA (10)

ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering2026Enhancing Visual Question Answering with Multimodal LLMs via Chain-of-Question Guided Retrieval-Augmented Generation2026Region-R1: Reinforcing Query-Side Region Cropping for Multi-Modal Re-Ranking2026WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering2026Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answering2026When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs2026CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering2026Reconstruction as a Bridge for Event-Based Visual Question Answering2025Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering2025Multimodal Rationales for Explainable Visual Question Answering2024