This paper investigates the influence of task-irrelevant context by formulating it as a controlled intervention within a binary visual judgment framework and reveals a robust geometric regularity: contextconditioned margins follow a consistent affine transformation of their context-free counterparts.
Yinfeng Wang, Zhiyuan Yao, Zheren Fu et al.· 0 citations
Extensive experiments show that Groc-PO achieves improved performance in hallucination mitigation, faithful reasoning, and overall reliability, supporting the value of more explicit grounded supervision for trustworthy multimodal reasoning.
Zhi Zheng, Zheren Fu, Zhiyuan Yao et al.· arXiv.org· 1 citation
This work provides an attention-based perspective on mitigating hallucinations by exploring the model's internal text-to-image cross-attention behaviors, and proposes ADAPT, an attention-based framework that intervenes directly on text-to-image cross-attention dynamics.