Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Paper
•
2402.05162
•
Published
•
1
Yangsibo Huang PRO
yangsibo
AI & ML interests
None yet
Recent Activity
authored
a paper
22 days ago
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank
Modifications
authored
a paper
22 days ago
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large
Language Models
authored
a paper
22 days ago
Fantastic Copyrighted Beasts and How (Not) to Generate Them
Organizations
yangsibo's activity
authored
7
papers
22 days ago
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
Paper
•
2406.16135
•
Published
Fantastic Copyrighted Beasts and How (Not) to Generate Them
Paper
•
2406.14526
•
Published
•
1
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
Paper
•
2406.14598
•
Published
Evaluating Copyright Takedown Methods for Language Models
Paper
•
2406.18664
•
Published
•
1
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
Paper
•
2407.06460
•
Published
On Memorization of Large Language Models in Logical Reasoning
Paper
•
2410.23123
•
Published
•
16
upvoted
a
paper
24 days ago
liked
a
model
24 days ago
upvoted
a
paper
24 days ago
updated
6
models
about 2 months ago
Cross-ling-mem/llama3-8b-wikitext103-hp-en
Text Generation
•
Updated
•
6
Cross-ling-mem/llama3-8b-wikitext103-hp-mixed-sentence8words
Text Generation
•
Updated
•
6
Cross-ling-mem/llama3-8b-wikitext103-hp-mixed-sentence
Text Generation
•
Updated
•
6
Cross-ling-mem/llama2-7b-wikitext103-hp-mixed-sentence8words
Text Generation
•
Updated
•
4
Cross-ling-mem/llama2-7b-wikitext103-hp-en
Text Generation
•
Updated
•
4
Cross-ling-mem/llama2-7b-wikitext103-hp-mixed-sentence
Text Generation
•
Updated
•
4
upvoted
a
paper
3 months ago
authored
2
papers
3 months ago
liked
a
Space
4 months ago