Model vs. User: Whose Values Prevail? Inference-Time Value Alignment in Multi-Turn Conversations
Human values shape how we expect language models to behave. Dominant alignment approaches treat values as global objectives, although the appropriate value orientation is personal and contextual. Training-free alignment can steer models toward target values at inference time, yet has been largely evaluated in single-tu...
Enrico Liscio, Anne Arzberger, Aditya Shankar et al.
· 1 citation