Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
Paper
•
2402.11746
•
Published
•
2
LLM Safety
Our research on LLM safety: red-teaming, value alignment, realignment.
-
-
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
Paper • 2308.09662 • Published • 3 -
Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases
Paper • 2310.14303 • Published • 1 -
declare-lab/starling-7B
Text Generation • Updated • 39 • 10 -
declare-lab/HarmfulQA
Viewer • Updated • 1.96k • 360 • 35 -
Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
Paper • 2406.11654 • Published • 6 -
WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models
Paper • 2408.03837 • Published • 18