Research map / Large language models / Alignment and preferences
A Human-Centric Pipeline for Aligning Large Language Models with Chinese Medical Ethics
Haoan Jin, Han Ying, Jiacheng Ji, Hanhui Xu, Mengyue Wu
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 |
|---|---|---|---|
| run more guardian-in-the-loop SFT rounds (round1 to round5) (ablation) | deepseek-r1-7b · MedES subjective | comprehensive score: 0.8862 -> 0.9356 | Improved |
| run more SFT rounds (round1 to round5) (ablation) | deepseek-r1-7b · MedES Emergency Care | accuracy (%): 43.7 -> 61.6 | Improved |
| run more SFT rounds (round1 to round5) (ablation) | deepseek-r1-7b · MedES Ethical Knowledge | accuracy (%): 36.7 -> 43.1 | Improved |
| run SFT round 4 to 5 in some scenarios (ablation) | deepseek-r1-7b · MedES subjective scenarios | scenario performance | Mixed |
| guardian-guided SFT of 7B model vs base | deepseek-r1-7b · MedES subjective | risk rate: 0.1624 -> 0.0320 | Improved |
| aligned 7B vs 671B model | deepseek-r1-7b-sft-round5 · MedES subjective | comprehensive score: 0.8103 -> 0.9356 | Improved |
| aligned 7B vs 671B model on objective drug safety | deepseek-r1-7b-sft-round5 · MedES Drug Safety | accuracy (%): 88.4 -> 52.8 | Hurt |
| add retrieval augmentation (RAG) to 7B model | deepseek-r1-7b · MedES Drug Safety | accuracy (%): 52.8 -> 82.4 | Improved |
Closest papers by meaning
- MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models (AAAI 2024 · similarity 0.89)
- Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-World Multi-Turn Dialogue (AAAI 2024 · similarity 0.87)
- LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models (NeurIPS 2024 · similarity 0.87)
- CareBot: A Pioneering Full-Process Open-Source Medical Language Model (AAAI 2025 · similarity 0.86)
- Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation (AAAI 2025 · similarity 0.85)
- MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey (NeurIPS 2024 · similarity 0.85)
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.
