SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
Paper
• 2511.08379 • Published
• 4
Giorgio Piras
giorgiopiras
·
AI & ML interests
Adversarial Machine Learning
Recent Activity
authored
a paper
6 days ago
Explaining Machine Learning DGA Detectors from DNS Traffic Data authored
a paper
6 days ago
SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models liked
a model 13 days ago
Beinsezii/llmfan46-Qwen3.5-27B-heretic-v2-GGUF-6.11BPW Organizations
None yet
upvoted a paper about 2 months ago