Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
This work addresses the need for better visually-situated natural language understanding, particularly for text-rich images, which is incremental as it builds on existing LLM extensions to the visual domain.
The paper tackles the problem of improving large language models' performance on text-rich images by introducing the Contrastive Reading Model (Cream), which enhances language-image understanding through a novel architecture and contrastive feature alignment, achieving compelling results in visual document understanding tasks.
Recent advances in Large Language Models (LLMs) have stimulated a surge of research aimed at extending their applications to the visual domain. While these models exhibit promise in generating abstract image captions and facilitating natural conversations, their performance on text-rich images still requires improvement. In this paper, we introduce Contrastive Reading Model (Cream), a novel neural architecture designed to enhance the language-image understanding capability of LLMs by capturing intricate details that are often overlooked in existing methods. Cream combines vision and auxiliary encoders, fortified by a contrastive feature alignment technique, to achieve a more effective comprehension of language information in visually situated contexts within the images. Our approach bridges the gap between vision and language understanding, paving the way for the development of more sophisticated Document Intelligence Assistants. Through rigorous evaluations across diverse visually-situated language understanding tasks that demand reasoning capabilities, we demonstrate the compelling performance of Cream, positioning it as a prominent model in the field of visual document understanding. We provide our codebase and newly-generated datasets at https://github.com/naver-ai/cream .