AI Paper Atlas

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

AAAI 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior · 1 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
run more guardian-in-the-loop SFT rounds (round1 to round5) (ablation)deepseek-r1-7b · MedES subjectivecomprehensive score: 0.8862 -> 0.9356Improved
run more SFT rounds (round1 to round5) (ablation)deepseek-r1-7b · MedES Emergency Careaccuracy (%): 43.7 -> 61.6Improved
run more SFT rounds (round1 to round5) (ablation)deepseek-r1-7b · MedES Ethical Knowledgeaccuracy (%): 36.7 -> 43.1Improved
run SFT round 4 to 5 in some scenarios (ablation)deepseek-r1-7b · MedES subjective scenariosscenario performanceMixed
guardian-guided SFT of 7B model vs basedeepseek-r1-7b · MedES subjectiverisk rate: 0.1624 -> 0.0320Improved
aligned 7B vs 671B modeldeepseek-r1-7b-sft-round5 · MedES subjectivecomprehensive score: 0.8103 -> 0.9356Improved
aligned 7B vs 671B model on objective drug safetydeepseek-r1-7b-sft-round5 · MedES Drug Safetyaccuracy (%): 88.4 -> 52.8Hurt
add retrieval augmentation (RAG) to 7B modeldeepseek-r1-7b · MedES Drug Safetyaccuracy (%): 52.8 -> 82.4Improved

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