Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models

TL;DR - Geo3R is a training-free, plug-and-play framework that uses geometric evidence and structured 3D reasoning to reduce spatial hallucinations in multimodal large language models.

• Defines spatial reasoning hallucination as errors caused by inadequate modeling of 3D scene structure.
• Targets perspective effects, object orientation, and viewpoint changes.
• Evaluated on three benchmarks spanning 18 tasks across these scenarios.
• Reportedly outperforms existing mitigation methods across diverse MLLMs without additional training.