Safeguard evaluation where scientific AI meets the lab: evidence across agent handoffs, calibration across interfaces, hazard under misleading labels.
JangKeun Kim
jang1563
AI & ML interests
None yet
Recent Activity
updated a dataset 9 days ago
jang1563/genelab-benchmark updated a dataset 10 days ago
jang1563/narrow-model-safety-eval updated a dataset 11 days ago
jang1563/clinical-trial-decision-benchmarkOrganizations
models 4
jang1563/constitutional-bioguard-v4
Text Classification • 0.2B • Updated • 12
jang1563/constitutional-bioguard-response
Text Classification • 0.2B • Updated
jang1563/constitutional-bioguard-deberta-v1
Text Classification • 0.2B • Updated • 14
jang1563/constitutional-bioguard-prompt
Text Classification • 0.2B • Updated
datasets 24
jang1563/narrow-model-safety-eval
Viewer • Updated • 8 • 986
jang1563/genelab-benchmark
Updated • 405
jang1563/clinical-trial-decision-benchmark
Viewer • Updated • 5.8k • 117
jang1563/llm-sfm-safety-eval
Viewer • Updated • 24.3k • 166
jang1563/sci-agent-verification-cascade
Viewer • Updated • 69 • 58
jang1563/biothreat-eval
Viewer • Updated • 72 • 60
jang1563/bio-overrefusal-v0.1
Viewer • Updated • 201 • 178
jang1563/SpaceOmicsBench-v3
Viewer • Updated • 26.9k • 159
jang1563/protein-structure-trust-benchmark
Viewer • Updated • 238 • 52
jang1563/evo2-spaceflight-vep
Viewer • Updated • 215k • 36