AI RESEARCH
When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
arXiv CS.AI
•
ArXi:2505.20214v2 Announce Type: replace Reasoning models have attracted increasing attention for their ability to tackle complex tasks, embodying the System II (slow thinking) paradigm in contrast to System I (fast, intuitive responses). Yet a key question remains: Does slower reasoning necessarily lead to truthful answers? Our findings suggest otherwise. We conduct the first systematic study of the inverse scaling law in slow-thinking paradigms for multimodal reasoning.