Contrastive-Guided Self-Supervised Latent Visual Reasoning for Hallucination Mitigation

Recent research on Large Vision-Language Models (LVLMs)has explored visual chain-of-thought (CoT) mechanisms to enhance visual-centric reasoning, effectively mitigating the hallucination issues that plaguecurrent models. However, existing paradigms typically rely on externalvisual tools and multi-turn interactions. While recent latent visual rea-soning approaches achieve tool-free, single-turn inference by supervisingintermediate representations with auxiliary images, they incur signifi-cant annotation costs. To address this, we propose Contrastive-GuidedSelf-Supervised Latent Visual Reasoning (CoLVR), a novel framework forself-supervised training of visual latent tokens in an annotation-free man-ner. Specifically, we leverage visual contrastive principles to identify keyvisual regions and employ Reinforcement Learning (RL) to align the gen-erated latent tokens with these salient regions. Extensive experimentson hallucination benchmarks demonstrate that our method significantlyoutperforms mainstream de-hallucination approaches and even surpassesfully supervised visual reasoning baselines.