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.
Stories per day · 30 days
2 RSS
2 stories, newest first · one card per story
Stories tagged #ethics
Mathematicians want proof OpenAI didn’t use their work
Mathematician Andreas Thom publicly accused OpenAI of opacity over whether ChatGPT conversations contributed to its non-sofic groups mathematics result.
1