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
upvoted a paper about 16 hours ago
Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict upvoted a paper 20 days ago
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents updated a model 5 months ago
jackzhang/openlm_3b_201305_dolci_think_300k_pre2013_sft_full-15500Organizations
models 8
jackzhang/openlm_3b_201305_dolci_think_300k_pre2013_sft_full-15500
Text Generation • 3B • Updated • 14
jackzhang/openlm_3b_201305_dolci_think_300k_pre2013_sft_full
Feature Extraction • 3B • Updated • 6
jackzhang/openlm_3b_201305_dolci_think_100k_pre2013_sft_full
3B • Updated • 3
jackzhang/Llama3.1-8B-Instruct-CoSAlign
8B • Updated • 7
jackzhang/newsspan.normalized.quip.100-1.bf
Updated
jackzhang/cnndm.normalized.quip.50-1.bf
Updated
jackzhang/newsspan.normalized.quip.50-1.bf
Updated
jackzhang/newsspan.normalized.quip.25-1.bf
Updated
datasets 38
jackzhang/ManyIH-Bench
Viewer • Updated • 853 • 19
jackzhang/mbpp-sanitized-withsig
Viewer • Updated • 427 • 32
jackzhang/mbpp-processed
Viewer • Updated • 500 • 13
jackzhang/JBDistill-Bench
Viewer • Updated • 1k • 110
jackzhang/wjharm-or79k-stage2
Viewer • Updated • 79.5k • 13
jackzhang/wjharm-or79k-stage1
Viewer • Updated • 79.5k • 14
jackzhang/cosalign_train_simplified
Viewer • Updated • 125k • 16
jackzhang/cosalign_test_simplfied
Viewer • Updated • 3.2k • 5
jackzhang/wjharm-or79k
Viewer • Updated • 159k • 11
jackzhang/wjtrain_prompts-advonly-held500
Viewer • Updated • 161k • 12