Research map / Vision-language and multimodal / Multimodal LLMs
DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding
Wenwen Yu, Zhibo Yang, Yuliang Liu, Xiang Bai
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace SFT with GRPO RL training (336 input, 4k) | Qwen2.5-VL-7B · DocVQA | score: 0.355 -> 0.579 | Improved |
| replace SFT with GRPO RL training (336 input, 4k) | Qwen2.5-VL-7B · TextVQA | score: 0.740 -> 0.802 | Improved |
| replace SFT with GRPO RL training (336 input, 4k) | Qwen2.5-VL-7B · GQA | score: 0.467 -> 0.546 | Improved |
| replace SFT with GRPO RL training (336 input, 4k) | Qwen2.5-VL-7B · Visual7W | score: 0.563 -> 0.580 | Improved |
| add RoI IoU reward (ablation) | DocThinker-7B · InfoQA | score: 0.637 -> 0.689 | Improved |
| add RoI IoU reward (ablation) | DocThinker-7B · TextCaps | score: 0.693 -> 0.738 | Improved |
| add rephrase question reward (ablation) | DocThinker-7B · TextVQA | score: 0.772 -> 0.827 | Improved |
| add rephrase question reward (ablation) | DocThinker-7B · DocVQA | score: 0.763 -> 0.795 | Improved |
| add both RoI IoU and rephrase question rewards (ablation) | DocThinker-7B · InfoQA | score: 0.602 -> 0.689 | Improved |
| add KL regularization beta=0.04 versus none (ablation) | DocThinker-7B · TextVQA | score: 0.803 -> 0.827 | Improved |
| increase KL beta from 0.001 to 0.04 (ablation) | DocThinker-7B · DocVQA | score: 0.785 -> 0.795 | Improved |
| increase input resolution from 336 to 1536 | DocThinker-7B · DocVQA | score: 0.579 -> 0.795 | Improved |
Closest papers by meaning
- DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding (AAAI 2026 · similarity 0.90)
- R-4B: Incentivizing General-Purpose Auto-Thinking in MLLMs via Bi-Mode Annealing and Reinforce Learning (CVPR 2026 · similarity 0.89)
- Revisual-R1: Advancing Multimodal Reasoning From Optimized Cold Start to Staged Reinforcement Learning (ICLR 2026 · similarity 0.88)
- DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding (CVPR 2026 · similarity 0.88)
- Markovian Transformers for Informative Language Modeling (ICLR 2026 · similarity 0.88)
- LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts (ICLR 2026 · similarity 0.88)
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.
