VisProve: Learning Typed Visual Provenance for Scientific Document Question Answering
cs.CV, cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering
- LoRA: Low-Rank Adaptation of Large Language Models
- Towards Self-Explainable Document Visual Question Answering with Chain-of-Explanation Predictions
- Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
- Decoupled Weight Decay Regularization
- CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
- GenerationPrograms: Fine-grained Attribution with Executable Programs
- UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding
- DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning
- TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
- SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning
- BERTScore: Evaluating Text Generation with BERT
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