Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education

TL;DR

This paper introduces Uni-Retrieval, a versatile retrieval framework designed for STEM education that supports multiple query styles, utilizing a new dataset and prompt tuning to improve retrieval accuracy and adaptability in educational scenarios.

Contribution

The paper presents a novel multi-style retrieval model with a dynamic prompt bank and a new STEM education retrieval dataset, enhancing retrieval performance for diverse educational queries.

Findings

Outperforms existing retrieval models in most tasks

Demonstrates scalability and robustness in educational retrieval scenarios

Effectively supports diverse query styles with prompt tuning

Abstract

In AI-facilitated teaching, leveraging various query styles to interpret abstract text descriptions is crucial for ensuring high-quality teaching. However, current retrieval models primarily focus on natural text-image retrieval, making them insufficiently tailored to educational scenarios due to the ambiguities in the retrieval process. In this paper, we propose a diverse expression retrieval task tailored to educational scenarios, supporting retrieval based on multiple query styles and expressions. We introduce the STEM Education Retrieval Dataset (SER), which contains over 24,000 query pairs of different styles, and the Uni-Retrieval, an efficient and style-diversified retrieval vision-language model based on prompt tuning. Uni-Retrieval extracts query style features as prototypes and builds a continuously updated Prompt Bank containing prompt tokens for diverse queries. This bank can updated during test time to represent domain-specific knowledge for different subject retrieval scenarios. Our framework demonstrates scalability and robustness by dynamically retrieving prompt tokens based on prototype similarity, effectively facilitating learning for unknown queries. Experimental results indicate that Uni-Retrieval outperforms existing retrieval models in most retrieval tasks. This advancement provides a scalable and precise solution for diverse educational needs.