New Paper on Ethical Preference Alignment

monojitchou · x · 2026-07-11

A forwarded post highlights a paper titled "Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models", which has been accepted by the Pluralistic Alignment Workshop @ ICML 2026 and will be presented as a poster.

Based on the title, the research focuses on using task vector composition for ethical preference alignment in language models, representing technical work in the value alignment and alignment methods space.

Original post →

More from AGI Musings

AGI Musings channel →