Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
Shu, Dong, Zhao, Haiyan, Hu, Jingyu, Liu, Weiru, Cheng, Lu, Du, Mengnan
–arXiv.org Artificial Intelligence
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and linguistic representations is not fully understood. This survey presents a comprehensive examination of alignment and misalignment in LVLMs through an explainability lens. We first examine the fundamentals of alignment, exploring its representational and behavioral aspects, training methodologies, and theoretical foundations. We then analyze misalignment phenomena across three semantic levels: object, attribute, and relational misalignment. Our investigation reveals that misalignment emerges from challenges at multiple levels: the data level, the model level, and the inference level. We provide a comprehensive review of existing mitigation strategies, categorizing them into parameter-frozen and parameter-tuning approaches. Finally, we outline promising future research directions, emphasizing the need for standardized evaluation protocols and in-depth explainability studies.
arXiv.org Artificial Intelligence
Jan-2-2025
- Country:
- North America > United States (0.28)
- Genre:
- Overview (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (1.00)
- Natural Language
- Chatbot (1.00)
- Large Language Model (1.00)
- Representation & Reasoning (1.00)
- Vision (1.00)
- Machine Learning > Neural Networks
- Information Technology > Artificial Intelligence