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-turn settings and with a single steering direction (e.g., toward safety). We evaluate four prompt- and activation-based steering methods in multi-turn conversations, where user and assistant models push toward the same or opposing, equally desirable values. We track alignment with a linear probe across three models and two value trade-offs. When assistant and user pull in oppo...
| Authors | Enrico Liscio, Anne Arzberger, Aditya Shankar et al. |
|---|---|
| Primary category | cs.CL |
| Published | 14 October 2026 |
| Last updated at source | 14 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.