Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels
cs.CV, cs.CL, cs.IR
Submitted: 2026-07-27
Updated: 2026-11-17
Code: https://github.com/hiyouga/EasyR1
Terminology
Sources
- Docling Technical Report
- Qwen3-VL Technical Report
- Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning
- Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
- Pix2seq: A Language Modeling Framework for Object Detection
- SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
- ContextCite: Attributing Model Generation to Context
- Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?
- LoRA: Low-Rank Adaptation of Large Language Models
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
- CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
- VISA: Retrieval Augmented Generation with Visual Source Attribution
- Teaching language models to support answers with verified quotes
- ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization
- DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
- Gemma 3 Technical Report
- MinerU: An Open-Source Solution for Precise Document Content Extraction
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