K and K

K-and-K's activity

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

yangsibo 

authored 7 papers 2 months ago

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

Paper • 2402.05162 • Published Feb 7, 2024 • 1

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

Paper • 2406.16135 • Published Jun 23, 2024

Fantastic Copyrighted Beasts and How (Not) to Generate Them

Paper • 2406.14526 • Published Jun 20, 2024 • 1

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

Paper • 2406.14598 • Published Jun 20, 2024

Evaluating Copyright Takedown Methods for Language Models

Paper • 2406.18664 • Published Jun 26, 2024 • 1

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Paper • 2407.06460 • Published Jul 8, 2024

On Memorization of Large Language Models in Logical Reasoning

Paper • 2410.23123 • Published Oct 30, 2024 • 18

alphapav 

updated 2 datasets 2 months ago

K-and-K/perturbed-knights-and-knaves

Viewer • Updated Oct 31, 2024 • 41.2k • 44 • 3

K-and-K/knights-and-knaves

Viewer • Updated Oct 31, 2024 • 6.9k • 93 • 3

yangsibo 

authored 2 papers 4 months ago

The Future of Open Human Feedback

Paper • 2408.16961 • Published Aug 15, 2024 • 21

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Paper • 2310.06987 • Published Oct 10, 2023

alphapav 

authored 3 papers 10 months ago

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Paper • 2403.01749 • Published Mar 4, 2024

Effective and Efficient Federated Tree Learning on Hybrid Data

Paper • 2310.11865 • Published Oct 18, 2023

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Paper • 2403.15447 • Published Mar 18, 2024 • 16

alphapav 

authored a paper over 1 year ago

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Paper • 2306.11698 • Published Jun 20, 2023 • 12