Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks
This work addresses the problem of integrating visual input into language models for multimodal tasks, offering an incremental approach to improve performance and transparency.
The study tackled whether language-only models can handle vision-language tasks by using verbalization models to encode visual information as text, finding that these models are effective even with limited samples and enhance interpretability.
Large language models have demonstrated robust performance on various language tasks using zero-shot or few-shot learning paradigms. While being actively researched, multimodal models that can additionally handle images as input have yet to catch up in size and generality with language-only models. In this work, we ask whether language-only models can be utilised for tasks that require visual input -- but also, as we argue, often require a strong reasoning component. Similar to some recent related work, we make visual information accessible to the language model using separate verbalisation models. Specifically, we investigate the performance of open-source, open-access language models against GPT-3 on five vision-language tasks when given textually-encoded visual information. Our results suggest that language models are effective for solving vision-language tasks even with limited samples. This approach also enhances the interpretability of a model's output by providing a means of tracing the output back through the verbalised image content.