Enhancing textual textbook question answering with large language models and retrieval augmented generation

Hessa Abdulrahman Alawwad, Areej Alhothali, Usman Naseem, Ali Alkhathlan, Amani Jamal
2/5/2024
cs.CLcs.AI

Official code: hessaAlawwad/PLR-TQA (5 stars, last commit 2025-08-04).

Abstract

Textbook question answering (TQA) is a challenging task in artificial intelligence due to the complex nature of context needed to answer complex questions. Although previous research has improved the task, there are still some limitations in textual TQA, including weak reasoning and inability to capture contextual information in the lengthy context. We propose a framework (PLRTQA) that incorporates the retrieval augmented generation (RAG) technique to handle the out-of-domain scenario where concepts are spread across different lessons, and utilize transfer learning to handle the long context and enhance reasoning abilities. Our architecture outperforms the baseline, achieving an accuracy improvement of 4. 12% in the validation set and 9. 84% in the test set for textual multiple-choice questions. While this paper focuses on solving challenges in the textual TQA, It provides a foundation for future work in multimodal TQA where the visual components are integrated to address more complex educational scenarios. Code: https://github.com/hessaAlawwad/PLR-TQA

View on arXivView PDF

Code Implementations(1)

hessaAlawwad/PLR-TQAOfficial100%

This repository implements the 2024 paper "Enhancing Textbook Question Answering with Llama-2 and RAG," achieving state-of-the-art results on the CK12-QA dataset.

52HTML, PythonDec 4, 20241 years ago

Similar Papers

Evaluating Multimodal Large Language Models on Educational Textbook Question Answering

88% match2025

KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?

83% match1 repo22024

HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA

83% match2024

AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs

83% match1 repo12023

Retrieval Augmented Generation for Domain-specific Question Answering

82% match2024

RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering

82% match1 repo532024

Cite this paper

@article{alawwad2024enhancing,
  title  = {Enhancing textual textbook question answering with large language models and retrieval augmented generation},
  author = {Hessa Abdulrahman Alawwad and Areej Alhothali and Usman Naseem and Ali Alkhathlan and Amani Jamal},
  year   = {2024},
  eprint = {2402.05128},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.05128v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.05128.svg)](https://codeofpaper.com/paper/2402.05128)

Discussion