✨Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models

📝 Summary:
Native omni-modal LLMs surprisingly show a visual preference, unlike traditional text-dominant models. This preference emerges in later layers and helps diagnose cross-modal hallucinations, improving model trustworthiness.

🔹 Publication Date: Published on Apr 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16902
• PDF: https://arxiv.org/pdf/2604.16902
• Github: https://github.com/icip-cas/OmniPreference

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#OmniModalLLM #ModalityPreference #AIHallucinations #TrustworthyAI #AIResearch