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
authored a paper 2 days ago
Jailbreak Distillation: Renewable Safety Benchmarking authored a paper 2 days ago
The Alignment Waltz: Jointly Training Agents to Collaborate for Safety authored a paper 2 days ago
Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in
Large Reasoning ModelsOrganizations
datasets 38
jackzhang/ManyIH-Bench
Viewer • Updated • 853 • 51
jackzhang/mbpp-sanitized-withsig
Viewer • Updated • 427 • 15
jackzhang/mbpp-processed
Viewer • Updated • 500 • 6
jackzhang/JBDistill-Bench
Viewer • Updated • 1k • 15
jackzhang/wjharm-or79k-stage2
Viewer • Updated • 79.5k • 10
jackzhang/wjharm-or79k-stage1
Viewer • Updated • 79.5k • 10
jackzhang/cosalign_train_simplified
Viewer • Updated • 125k • 19
jackzhang/cosalign_test_simplfied
Viewer • Updated • 3.2k • 24
jackzhang/wjharm-or79k
Viewer • Updated • 159k • 13
jackzhang/wjtrain_prompts-advonly-held500
Viewer • Updated • 161k • 5