Vision-Language Models under Cultural and Inclusive Considerations

Autor:	Karamolegkou, Antonia, Rust, Phillip, Cao, Yong, Cui, Ruixiang, Søgaard, Anders, Hershcovich, Daniel
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Computers and Society
Druh dokumentu:	Working Paper
Popis:	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 context of this use case. To address this problem, we create a survey to determine caption preferences and propose a culture-centric evaluation benchmark by filtering VizWiz, an existing dataset with images taken by people who are blind. We then evaluate several VLMs, investigating their reliability as visual assistants in a culturally diverse setting. While our results for state-of-the-art models are promising, we identify challenges such as hallucination and misalignment of automatic evaluation metrics with human judgment. We make our survey, data, code, and model outputs publicly available. Comment: HuCLLM @ ACL 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.06177 Zobrazit plný text záznamu View this record from Arxiv