3 papers
cs.AI2026
LaVGuard: Selective Decoding for Contextual Value Drift
Jiale Dai, Liuxian Ma, Hongcan Deng +5
A content-safe response can still promote priorities that conflict with its task: an assistant may demand compliance when asked to preserve autonomy. We study contextual value drif…
cs.AI2026
Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering
Jiale Dai, Hongcan Deng, Liuxian Ma +2
Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Conventional activation edits often cha…
cs.AI2026
VISTA: Value-Informed Event Appraisal for Multimodal Emotion Conflict
Jiale Dai, Liuxian Ma, Xiaoke Niu +5
Conflicting emotional cues can be individually valid: a subdued voice may reflect a blocked goal while a smile satisfies a social obligation. Their interpretation depends on what t…