mlsanityData to 7 Oct 2026

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

arXiv 2402.05128 ↗First posted 5 Feb 2024cs.CL cs.AIcited by 13

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

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

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 15 of its 39 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

15 of 39 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  5. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  6. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  7. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  8. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  9. 2023Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Familycited by 71
  10. 2019Multi-Hop Paragraph Retrieval for Open-Domain Question Answeringcited by 34
  11. 2023Improving Retrieval-Augmented Large Language Models via Data Importance Learningcited by 17
  12. 2022Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligencecited by 16
3 more
  1. 2020ISAAQ -- Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attentioncited by 14
  2. 2023Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language modelcited by 14
  3. 2020XTQA: Span-Level Explanations of the Textbook Question Answeringcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 2.

13 papers.

Sort:

By area:

  1. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  2. 2024Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimizationcited by 22
  3. 2024Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimizationcited by 17
  4. 2025Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoningcited by 11
  5. 2025MELLM: A Flow-Guided Large Language Model for Micro-Expression Understandingcited by 2
  6. 2025Enhancing Frame Detection with Retrieval Augmented Generationcited by 1
  7. 2025Evaluating Multimodal Large Language Models on Educational Textbook Question Answeringcited by 1
  8. 2025Physical Plausibility Reasoning via HCM-GRPO: Empowering Compact Model for Superior Performancecited by 1
  9. 2025Beyond Retrieval: Joint Supervision and Multimodal Document Ranking for Textbook Question Answeringcited by 0
  10. 2025Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Makingcited by 0
  11. 2025ALIVE: An Avatar-Lecture Interactive Video Engine with Content-Aware Retrieval for Real-Time Interactioncited by 0
  12. 2026Towards Privacy-Preserving Mental Health Support with Large Language Modelscited by 0
1 more
  1. 2026TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Generation from Science Curriculum Materialscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
  2. 2024RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
  3. 2024Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU
  4. 2024KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?
  5. 2025Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook
  6. 2025LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation
  7. 2025RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning
  8. 2025Answering Students' Questions on Course Forums Using Multiple Chain-of-Thought Reasoning and Finetuning RAG-Enabled LLM