Graphionale: How Graph Visualizations of LLM Rationales Affect Human Decision Making
Graphionale is developed as a testbed for empirically studying argument-map-style rationale visualization, and its findings contribute empirical design knowledge about when and how graphical rationales support human decision making, and inform the next-generation reasoning-aware AI interfaces.
Xinru Wang, Zhexue Ma, Ming Yin et al.
· 0 citations