🟢
Open to AI PM / LLM eval roles
Pinned Loading
-
ectd-assembler
ectd-assembler PublicNMPA eCTD submission dossier assembler with per-claim evidence chain — messy PDF/Word/Excel sources → compliant package (index.xml + M1–M5), every value traceable to its source cell. 脏源文件→合规申报包,逐字段…
-
llm-wiki
llm-wiki PublicFive-regulator pharma guidance corpus & incremental pipeline · CDE 647 / FDA 1182 / EMA 811 full text + PMDA 819 / ICH 160 index-only, 3,619 entries (zh/en/ja) with QA ledgers & retrieval benchmark…
Python
-
pharma-llm-risk-eval
pharma-llm-risk-eval PublicPharma-vertical LLM risk & reliability evaluation: regulatory faithfulness / medication safety / dual-use boundary. Frozen gold sets + Wilson stratified metrics + regression gates. 医药垂域 LLM 风险评测:监管…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.