Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
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.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeLanguage ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Vision-Language Models under Cultural and Inclusive Considerations
Large vision-language models (VLMs) can assist visually impaired people by describing images from their daily lives. Current evaluation datasets may not reflect diverse cultural user backgrounds or the situational contex…
HallucinationSurveyPerception of Misalignment States for Sky Survey Telescopes with the Digital Twin and the Deep Neural Networks
Sky survey telescopes play a critical role in modern astronomy, but misalignment of their optical elements can introduce significant variations in point spread functions, leading to reduced data quality. To address this,…
AstronomyThe Great Misalignment Problem in Human Evaluation of NLP Methods
We outline the Great Misalignment Problem in natural language processing research, this means simply that the problem definition is not in line with the method proposed and the human evaluation is not in line with the de…
Hypothesis Testing for Quantifying LLM-Human Misalignment in Multiple Choice Settings
As Large Language Models (LLMs) increasingly appear in social science research (e.g., economics and marketing), it becomes crucial to assess how well these models replicate human behavior. In this work, using hypothesis …
Decision MakingLanguage ModelingLanguage ModellingMarketing+1Emergent Misalignment is Easy, Narrow Misalignment is Hard
Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered surv…