MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answering
cs.CV
Submitted: 2025-11-15
Updated: 2025-12-18
Code: https://github.com/seokwon99/MAVIS
Terminology
Sources
- Phi-4 Technical Report
- CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
- Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
- HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles
- Are We on the Right Way for Evaluating Large Vision-Language Models?
- ELI5: Long Form Question Answering
- Enabling Large Language Models to Generate Text with Citations
- RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
- DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
- Training Language Models to Generate Text with Citations via Fine-grained Rewards
- Long-Form Answers to Visual Questions from Blind and Low Vision People
- GPT-4o System Card
- Mixtral of Experts
- FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models
- AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization
- LLaVA-OneVision: Easy Visual Task Transfer
- Improving Attributed Text Generation of Large Language Models via Preference Learning
- Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling
- Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models
- MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs