SOURCE-LINKED INTELLIGENCE

Probing the Structure and Dynamics of LLM Value Expression through Value Conflicts

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Ethical evaluation of Large Language Models (LLMs) often characterizes model values as static and monolithic. In contrast, we argue that LLM value expression is better understood as a structured yet dynamic phenomenon. To investigate this, we introduce Conflict-driven Value Probing, a controlled framework that places LLMs in value conflicts and implements four types of interventions that perturb these conflicts to probe LLM value expression. Applying this framework to ten LLMs, we identify three recurring patterns. (1) Expression duality: models shift from broad idealistic orientations in abst

Read original source ↗ Open in workspace

recordType

paper

region

Global