Research map / Large language models / Language, safety and interpretability
SAT-RRG: LLM-Guided Self-Adaptive Training for Radiology Report Generation with Token-Level Push-Pull Optimization
Yunyi Liu, Yingshu Li, Tong Chen, Lingqiao Liu, Lei Wang, Luping Zhou
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 |
|---|---|---|---|
| add ETAPL error-token penalty loss (ablation) | CE baseline · MIMIC-CXR | BLEU-4: 0.131 -> 0.136 | Improved |
| add CTAL correct-token loss (ablation) | CE baseline · MIMIC-CXR | BLEU-4: 0.131 -> 0.141 | Improved |
| add ETAPL on top of CTAL (ablation) | CTAL · MIMIC-CXR | BLEU-4: 0.141 -> 0.143 | Improved |
| add focal weighting (ablation) | entropy-only SAT-RRG · MIMIC-CXR | BLEU-4: 0.139 -> 0.143 | Improved |
| add entropy weighting (ablation) | focal-only SAT-RRG · MIMIC-CXR | BLEU-4: 0.141 -> 0.143 | Improved |
| increase focal gamma from 1.5 to 2.0 (ablation) | SAT-RRG · MIMIC-CXR | BLEU-4: 0.143 -> 0.141 | Hurt |
| decrease focal gamma from 1.5 to 1.0 (ablation) | SAT-RRG · MIMIC-CXR | BLEU-4: 0.143 -> 0.139 | Hurt |
| train with SAT-RRG token-level push-pull losses | LLaMA3-3B report generator · IU-Xray | BLEU-4: 0.190 -> 0.196 vs EKAGen | Improved |
| SAT-RRG vs EKAGen on RadCliQ | SAT-RRG · MIMIC-CXR | RadCliQ: 1.126 -> 1.150 | Hurt |
Closest papers by meaning
- LLM-RG4: Flexible and Factual Radiology Report Generation Across Diverse Input Contexts (AAAI 2025 · similarity 0.90)
- Bootstrapping Large Language Models for Radiology Report Generation (AAAI 2024 · similarity 0.89)
- CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation (CVPR 2026 · similarity 0.87)
- HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generation (AAAI 2025 · similarity 0.87)
- ReFINE: A Reward-Based Framework for Interpretable and Nuanced Evaluation of Radiology Report Generation (AAAI 2026 · similarity 0.87)
- S2D-Align: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation (AAAI 2026 · similarity 0.87)
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.
