Knowledge Tagging System on Math Questions via LLMs with Flexible Demonstration Retriever

TL;DR

This paper demonstrates that Large Language Models can effectively automate knowledge tagging for math questions, outperforming traditional encoding-based methods, especially in complex cases, by using a reinforcement learning-based demonstration retriever.

Contribution

The paper introduces a novel approach combining LLMs with a reinforcement learning-based demonstration retriever for improved knowledge tagging in math questions.

Findings

LLMs achieve strong zero- and few-shot performance on math knowledge tagging

The reinforcement learning-based retriever enhances demonstration efficiency and model performance

The method outperforms traditional semantic similarity-based tagging approaches

Abstract

Knowledge tagging for questions plays a crucial role in contemporary intelligent educational applications, including learning progress diagnosis, practice question recommendations, and course content organization. Traditionally, these annotations are always conducted by pedagogical experts, as the task requires not only a strong semantic understanding of both question stems and knowledge definitions but also deep insights into connecting question-solving logic with corresponding knowledge concepts. With the recent emergence of advanced text encoding algorithms, such as pre-trained language models, many researchers have developed automatic knowledge tagging systems based on calculating the semantic similarity between the knowledge and question embeddings. In this paper, we explore automating the task using Large Language Models (LLMs), in response to the inability of prior encoding-based methods to deal with the hard cases which involve strong domain knowledge and complicated concept definitions. By showing the strong performance of zero- and few-shot results over math questions knowledge tagging tasks, we demonstrate LLMs' great potential in conquering the challenges faced by prior methods. Furthermore, by proposing a reinforcement learning-based demonstration retriever, we successfully exploit the great potential of different-sized LLMs in achieving better performance results while keeping the in-context demonstration usage efficiency high.