Guiding Multimodal Large Language Models with Blind and Low Vision People Visual Questions for Proactive Visual Interpretations
This addresses inefficiencies in visual interpretation applications for BLV users, offering an incremental improvement by leveraging existing data to tailor outputs.
The paper tackles the problem of multimodal large language models (MLLMs) providing irrelevant, lengthy descriptions for Blind and Low Vision (BLV) users by developing a system that uses historical BLV questions to guide MLLMs for more context-aware interpretations, resulting in 76.1% of descriptions anticipating user questions and 54.4% preference over context-free descriptions.
Multimodal large language models (MLLMs) have been integrated into visual interpretation applications to support Blind and Low Vision (BLV) users because of their accuracy and ability to provide rich, human-like interpretations. However, these applications often default to comprehensive, lengthy descriptions regardless of context. This leads to inefficient exchanges, as users must go through irrelevant details rather than receiving the specific information they are likely to seek. To deliver more contextually-relevant information, we developed a system that draws on historical BLV users questions. When given an image, our system identifies similar past visual contexts from the VizWiz-LF dataset and uses the associated questions to guide the MLLM generate descriptions more relevant to BLV users. An evaluation with three human labelers who revised 92 context-aware and context-free descriptions showed that context-aware descriptions anticipated and answered users' questions in 76.1% of cases (70 out of 92) and were preferred in 54.4% of comparisons (50 out of 92). Our paper reviews, and data analysis are publicly available in a Github repository at https://github.com/rgonzalezp/guiding-multimodal-large-language-models-with-blind-and-low-vision-people-visual-questions .