Enhancing textual textbook question answering with large language models and retrieval augmented generation
This work addresses challenges in textual TQA for educational AI, though it is incremental as it builds on existing methods like RAG.
The paper tackled the problem of textual textbook question answering (TQA) by proposing a framework (PLRTQA) that uses retrieval augmented generation (RAG) and transfer learning to improve reasoning and handle long contexts, resulting in accuracy improvements of 4.12% on validation and 9.84% on test sets.
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