Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models
Researchers build a 12,000-dilemma multilingual dataset and use orthogonalized task vectors to isolate and steer ethical value preferences in LLMs.
1 stories, newest first · one card per story
Researchers build a 12,000-dilemma multilingual dataset and use orthogonalized task vectors to isolate and steer ethical value preferences in LLMs.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views