arXiv CS AI
techCenter
Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignmenttranslating…
arXiv:2609.05800v1 Announce Type: new
Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods handle one concept at a time. Pluralistic alignment, where different stakeholders need different value…
Keywords#Alignment#LLM#Pluralistic#Steering#LLM Alignment