Yangsibo Huang PRO

yangsibo's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored 7 papers about 2 months ago

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

Paper • 2402.05162 • Published Feb 7 • 1

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

Paper • 2406.16135 • Published Jun 23

Fantastic Copyrighted Beasts and How (Not) to Generate Them

Paper • 2406.14526 • Published Jun 20 • 1

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

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Paper • 2407.06460 • Published Jul 8

On Memorization of Large Language Models in Logical Reasoning

Paper • 2410.23123 • Published Oct 30 • 18

upvoted a paper about 2 months ago

Stealing User Prompts from Mixture of Experts

Paper • 2410.22884 • Published Oct 30 • 14

liked a model about 2 months ago

muse-bench/MUSE-news_target

Text Generation • Updated May 31 • 1.77k • 2

upvoted a paper about 2 months ago

On Memorization of Large Language Models in Logical Reasoning

Paper • 2410.23123 • Published Oct 30 • 18

updated 6 models 3 months ago

Cross-ling-mem/llama3-8b-wikitext103-hp-en

Text Generation • Updated Sep 30 • 14

Cross-ling-mem/llama3-8b-wikitext103-hp-mixed-sentence8words

Text Generation • Updated Sep 30 • 18

Cross-ling-mem/llama3-8b-wikitext103-hp-mixed-sentence

Text Generation • Updated Sep 30 • 16

Cross-ling-mem/llama2-7b-wikitext103-hp-mixed-sentence8words

Text Generation • Updated Sep 30 • 9

Cross-ling-mem/llama2-7b-wikitext103-hp-en

Text Generation • Updated Sep 30 • 26

Cross-ling-mem/llama2-7b-wikitext103-hp-mixed-sentence

Text Generation • Updated Sep 30 • 6

upvoted a paper 4 months ago

The Future of Open Human Feedback

Paper • 2408.16961 • Published Aug 15 • 21

authored 2 papers 4 months ago

The Future of Open Human Feedback

Paper • 2408.16961 • Published Aug 15 • 21

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Paper • 2310.06987 • Published Oct 10, 2023

liked a Space 5 months ago

Runtime error

2

🥇

Muse Leaderboard