Boyi Wei

boyiwei

boyiwei

AI & ML interests

None yet

Recent Activity

updated a dataset 15 days ago

boyiwei/BenignBio

updated a Space about 1 month ago

boyiwei/CoTaEval_leaderboard

View all activity

Organizations

boyiwei's activity

updated a dataset 15 days ago

boyiwei/BenignBio

Viewer • Updated 15 days ago • 100 • 19

updated a Space about 1 month ago

Running

🚀

CoTaEval Leaderboard

updated a dataset 3 months ago

boyiwei/BeaverTails-Disjoint-Deduplicated

Viewer • Updated Sep 22 • 4.99k • 37

liked a dataset 4 months ago

boyiwei/CoTaEval

Viewer • Updated Jun 22 • 5.2k • 106 • 4

authored 2 papers 4 months ago

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors

Paper • 2406.14598 • Published Jun 20

Evaluating Copyright Takedown Methods for Language Models

Paper • 2406.18664 • Published Jun 26 • 1

upvoted 2 papers 4 months ago

Evaluating Copyright Takedown Methods for Language Models

Paper • 2406.18664 • Published Jun 26 • 1

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Paper • 2402.05162 • Published Feb 7 • 1

updated 3 models 5 months ago

updated a dataset 6 months ago

boyiwei/CoTaEval

Viewer • Updated Jun 22 • 5.2k • 106 • 4

updated 4 models 7 months ago

boyiwei/llama2-7b_chat_newsqa_PO_5e-5_4

Text Generation • Updated Jun 10 • 11

boyiwei/llama2-7b_chat_newsqa_KL_2e-6_1

Text Generation • Updated Jun 10 • 8

boyiwei/llama2-7b_chat_newsqa_GD_3e-6_1

Text Generation • Updated Jun 9 • 11

boyiwei/llama2-7b_chat_newsqa_GA_1.5e-6_1

Text Generation • Updated Jun 9 • 12

updated 2 datasets 7 months ago

boyiwei/copyright_unlearning

Viewer • Updated May 28 • 6k • 63

boyiwei/newsqa_filtered_sorted

Viewer • Updated May 23 • 69.4k • 5

updated a dataset 8 months ago

boyiwei/newsqa

Viewer • Updated Apr 21 • 103k • 34

liked a model 8 months ago

meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • Updated Sep 27 • 1.78M • • 3.71k