Enhancing textual textbook question answering with large language models and retrieval augmented generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913660336603136 |
|---|---|
| author | Alawwad, Hessa Abdulrahman Alhothali, Areej Naseem, Usman Alkhathlan, Ali Jamal, Amani |
| author_facet | Alawwad, Hessa Abdulrahman Alhothali, Areej Naseem, Usman Alkhathlan, Ali Jamal, Amani |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05128 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing textual textbook question answering with large language models and retrieval augmented generation Alawwad, Hessa Abdulrahman Alhothali, Areej Naseem, Usman Alkhathlan, Ali Jamal, Amani Computation and Language Artificial Intelligence 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 |
| title | Enhancing textual textbook question answering with large language models and retrieval augmented generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.05128 |