Artifacts for paper "Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements" (https://arxiv.org/abs/2410.08968)
Jack Zhang
jackzhang
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
jhu-clsp/ManyIH-Bench published a dataset 1 day ago
jhu-clsp/ManyIH-Bench updated a dataset 3 days ago
jackzhang/ManyIH-BenchOrganizations
datasets 38
jackzhang/ManyIH-Bench
Viewer • Updated • 853 • 27
jackzhang/mbpp-sanitized-withsig
Viewer • Updated • 427 • 18
jackzhang/mbpp-processed
Viewer • Updated • 500 • 9
jackzhang/JBDistill-Bench
Viewer • Updated • 1k • 21
jackzhang/wjharm-or79k-stage2
Viewer • Updated • 79.5k • 10
jackzhang/wjharm-or79k-stage1
Viewer • Updated • 79.5k • 14
jackzhang/cosalign_train_simplified
Viewer • Updated • 125k • 19
jackzhang/cosalign_test_simplfied
Viewer • Updated • 3.2k • 18
jackzhang/wjharm-or79k
Viewer • Updated • 159k • 17
jackzhang/wjtrain_prompts-advonly-held500
Viewer • Updated • 161k • 7