Uni-SMART


Universal Science Multimodal Analysis and Research Transformer
Descriptive Alt Text

Product Trial

You can test the latest Uni-SMART model in this trial product: https://uni-finder.dp.tech/

Abstract

In scientific research and its application, scientific literature analysis is crucial as it allows researchers to build on the work of others. However, the fast growth of scientific knowledge has led to a massive increase in scholarly articles, making in-depth literature analysis increasingly challenging and time-consuming. The emergence of Large Language Models (LLMs) has offered a new way to address this challenge. Known for their strong abilities in summarizing texts, LLMs are seen as a potential tool to improve the analysis of scientific literature. However, existing LLMs have their own limits. Scientific literature often includes a wide range of multimodal elements, such as molecular structure, tables, and charts, which are hard for text-focused LLMs to understand and analyze. This issue points to the urgent need for new solutions that can fully understand and analyze multimodal content in scientific literature. To answer this demand, we present Uni-SMART (Universal Science Multimodal Analysis and Research Transformer), an innovative model designed for in-depth understanding of multimodal scientific literature. Through rigorous quantitative evaluation across several domains, Uni-SMART demonstrates superior performance over leading text-focused LLMs. Furthermore, our exploration extends to practical applications, including patent infringement detection and nuanced analysis of charts. These applications not only highlight Uni-SMART's adaptability but also its potential to revolutionize how we interact with scientific literature.

Evaluation of Uni-SMART(partial)

Evaluation on table data

Description of the image

Evaluation on chart data

Description of the image

Evaluation on molecule data

Description of the image

Evaluation on reactions data

Description of the image

Example of Uni-SMART

Infringement Analysis

Description of the image

Chart analysis

Description of the image

Sci-Assess

This paper utilizes the Sci-Assess benchmark. For more details, please refer to Sci-Assess.