AI Paper Atlas

Research map / Large language models / Agents, code and math

Beyond N-grams: A Hierarchical Reward Learning Framework for Clinically-Aware Medical Report Generation

Yuan Wang, Shujian Gao, Jiaxiang Liu, Songtao Jiang, Xia Haoxiang, Xiaotian Zhang, Zhaolu Kang, Yemin Wang, Zuozhu Liu

AAAI 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
add semantic-level LLM-verifier reward on top of token and concept rewards (ablation)HiMed-3B · MIMIC-CXRROUGE-L: 0.258 -> 0.271Improved
add semantic-level LLM-verifier reward on top of token and concept rewards (ablation)HiMed-3B · CheXpertROUGE-L: 0.138 -> 0.157Improved
add semantic-level LLM-verifier reward on top of token and concept rewards (ablation)HiMed-3B · IU-XrayROUGE-L: 0.301 -> 0.319Improved
use dynamic linear reward weight adjustment instead of fixed weights (ablation)HiMed-3B · MIMIC-CXRRaTEScore: 0.525 -> 0.544Improved
set alpha_min 0.1 rather than 0.3 in linear schedule (ablation)HiMed-3B · MIMIC-CXRRaTEScore: 0.535 -> 0.544Improved
set alpha_min 0.1 rather than 0.0 in linear schedule (ablation)HiMed-3B · MIMIC-CXRRaTEScore: 0.541 -> 0.544No clear effect
use larger Qwen3-30B-A3B verifier instead of 7-8B verifiers (ablation)HiMed-3B · CheXpertROUGE-L: 0.135 -> 0.157Improved
use small 7-8B verifiers instead of no semantic reward (ablation)HiMed-3B · CheXpertROUGE-L: 0.138 -> 0.134No clear effect
add RL fine-tuning after cold-start SFT (ablation)HiMed-3B · MIMIC-CXR, CheXpert, IU-Xrayreport qualityImproved
HiMed-3B vs strongest baseline out of domainHiMed-3B · PadChest-GR (out-of-domain, English)RaTEScore: 0.348 -> 0.371Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy