# Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education

arXiv: https://arxiv.org/abs/2402.14293 · HTML: https://mlsanity.com/paper/2402.14293/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 66 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations](https://mlsanity.com/paper/1511.02301/) (2015)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models](https://mlsanity.com/paper/2303.13809/) (2023)
- [Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers](https://mlsanity.com/paper/2311.09000/) (2023)
- [Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension](https://mlsanity.com/paper/2203.13947/) (2022)
- [Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family](https://mlsanity.com/paper/2303.07992/) (2023)
- [VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping](https://mlsanity.com/paper/2304.07810/) (2023)
- [Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders](https://mlsanity.com/paper/2105.03505/) (2021)
- [Integrating UMLS Knowledge into Large Language Models for Medical Question Answering](https://mlsanity.com/paper/2310.02778/) (2023)
- [TutorialBank: A Manually-Collected Corpus for Prerequisite Chains, Survey Extraction and Resource Recommendation](https://mlsanity.com/paper/1805.04617/) (2018)
- [Incorporating Structured Sentences with Time-enhanced BERT for Fully-inductive Temporal Relation Prediction](https://mlsanity.com/paper/2304.04717/) (2023)
- [R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning](https://mlsanity.com/paper/2004.10610/) (2020)
- [NLPBench: Evaluating Large Language Models on Solving NLP Problems](https://mlsanity.com/paper/2309.15630/) (2023)
- [PubGraph: A Large-Scale Scientific Knowledge Graph](https://mlsanity.com/paper/2302.02231/) (2023)

## Built on by (most cited first, 3 of 3)

- [A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding](https://mlsanity.com/paper/2407.01976/) (2024)
- [KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques](https://mlsanity.com/paper/2403.05881/) (2024)
- [Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors](https://mlsanity.com/paper/2502.13311/) (2025)

## Abstract (arXiv)

In the domain of Natural Language Processing (NLP), Large Language Models (LLMs) have demonstrated promise in text-generation tasks. However, their educational applications, particularly for domain-specific queries, remain underexplored. This study investigates LLMs' capabilities in educational scenarios, focusing on concept graph recovery and question-answering (QA). We assess LLMs' zero-shot performance in creating domain-specific concept graphs and introduce TutorQA, a new expert-verified NLP-focused benchmark for scientific graph reasoning and QA. TutorQA consists of five tasks with 500 QA pairs. To tackle TutorQA queries, we present CGLLM, a pipeline integrating concept graphs with LLMs for answering diverse questions. Our results indicate that LLMs' zero-shot concept graph recovery is competitive with supervised methods, showing an average 3% F1 score improvement. In TutorQA tasks, LLMs achieve up to 26% F1 score enhancement. Moreover, human evaluation and analysis show that CGLLM generates answers with more fine-grained concepts.