نسخة أولية وصول مفتوح
ROT: Rotating Hidden States towards Contextual Vectors for Hallucination Mitigation in LVLMs
Large Vision-Language Models (LVLMs) frequently suffer from object hallucination. Existing training-free interventions primarily manipulate attention weights, which indirectly affect the deep semantics reaching the final predictive layers. In this work, we shift our focus to the hidden state vectors extracted after sel …