paper-with-me

Papers

Efficient Medical VIE via Reinforcement Learning

2025-06-16 · Lijun Liu, Ruiyang Li, Zhaocheng Liu, Chenglin Zhu, Chong Li, Jiehan Cheng, Qiang Ju, Jian Xie

Visual Information Extraction (VIE) converts unstructured document images into structured formats like JSON, critical for medical applications such as report analysis and online consultations. Traditional methods rely on OCR and language models, while end-to-end multimodal models offer direct JSON generation. However, domain-specific schemas and high annotation costs limit their effectiveness in medical VIE. We base our approach on the Reinforcement Learning with Verifiable Rewards (RLVR) framework to address these challenges using only 100 annotated samples. Our approach ensures dataset diversity, a balanced precision-recall reward mechanism to reduce hallucinations and improve field coverage, and innovative sampling strategies to enhance reasoning capabilities. Fine-tuning Qwen2.5-VL-7B with our RLVR method, we achieve state-of-the-art performance on medical VIE tasks, significantly improving F1, precision, and recall. While our models excel on tasks similar to medical datasets, performance drops on dissimilar tasks, highlighting the need for domain-specific optimization. Case studies further demonstrate the value of reasoning during training and inference for VIE.

📄 PDF Abstract BibTeX arXiv:2506.13363

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityOptical Character Recognition (OCR)reinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Reinforcement Learning in Medical Image Analysis: Concepts, Applications, Challenges, and Future Directions

2022-06-28 · Mingzhe Hu, Jiahan Zhang, Luke Matkovic, Tian Liu 외

Motivation: Medical image analysis involves tasks to assist physicians in qualitative and quantitative analysis of lesions or anatomical structures, significantly improving the accuracy and reliability of diagnosis and p…

ArticlesMedical Image AnalysisPrognosisreinforcement-learning+2

AI Assisted Annotator using Reinforcement Learning

2019-10-02 · V. Ratna Saripalli, Gopal Avinash, Dibyajyoti Pati, Michael Potter 외

Healthcare data suffers from both noise and lack of ground truth. The cost of data increases as it is cleaned and annotated in healthcare. Unlike other data sets, medical data annotation, which is critical to accurate gr…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation

2025-08-18 · Yizhou Liu, Dingkang Yang, Zizhi Chen, Minghao Han 외 arxiv

Reinforcement learning (RL) with rule-based reward functions has recently shown great promise in enhancing the reasoning depth and generalization ability of vision-language models (VLMs), while maintaining computational …

Visual Question AnsweringComputational EfficiencyReinforcement LearningMultimodal Reasoning

Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning

2025-05-25 · Shaohao Rui, Kaitao Chen, Weijie Ma, Xiaosong Wang

Recent advances in reinforcement learning with verifiable, rule-based rewards have greatly enhanced the reasoning capabilities and out-of-distribution generalization of VLMs/LLMs, obviating the need for manually crafted …

Out-of-Distribution Generalizationreinforcement-learningReinforcement LearningVisual Question Answering (VQA)+1

Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation

2026-02-11 · Guangjing Yang, ZhangYuan Yu, Ziyuan Qin, Xinyuan Song 외 arxiv

While recent advances in Reinforcement Fine-Tuning (RFT) have shown that rule-based reward schemes can enable effective post-training for large language models, their extension to cross-modal, vision-centric domains rema…