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

arXiv: https://arxiv.org/abs/2406.13885 · HTML: https://mlsanity.com/paper/2406.13885/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://mlsanity.com/paper/2209.14610/) (2022)
- [EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction](https://mlsanity.com/paper/1906.05658/) (2019)
- [RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning](https://mlsanity.com/paper/2305.14502/) (2023)
- [DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections](https://mlsanity.com/paper/2102.13247/) (2021)
- [Dynamic Demonstrations Controller for In-Context Learning](https://mlsanity.com/paper/2310.00385/) (2023)

## Built on by (most cited first, 6 of 6)

- [Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs](https://mlsanity.com/paper/2409.16490/) (2024)
- [Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing](https://mlsanity.com/paper/2410.01727/) (2024)
- [Knowledge Tagging with Large Language Model based Multi-Agent System](https://mlsanity.com/paper/2409.08406/) (2024)
- [Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues](https://mlsanity.com/paper/2507.06910/) (2025)
- [A LLM-Driven Multi-Agent Systems for Professional Development of Mathematics Teachers](https://mlsanity.com/paper/2507.05292/) (2025)
- [EUR-USD Exchange Rate Forecasting Based on Information Fusion with Large Language Models and Deep Learning Methods](https://mlsanity.com/paper/2408.13214/) (2024)

## Abstract (arXiv)

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.