LLM-Tuning-Safety

AI & ML interests

None defined yet.

Recent Activity

breakend  authored a paper about 1 month ago

On the Opportunities and Risks of Foundation Models

breakend  authored a paper about 1 month ago

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

breakend  authored a paper about 1 month ago

LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

View all activity

Team members 4