Abstract
In this paper, we investigate and introduce a novel Llama-2 based model, fine-tuned with an original dataset designed to mirror real-world mathematical challenges. The dataset was collected through a question-answering platform, incorporating solutions generated by both rule-based solver and question answering, to cover a broad spectrum of mathematical concepts and problem-solving techniques. Experimental results demonstrate significant performance improvements when the models are fine-tuned with our dataset. The results suggest that the integration of contextually rich and diverse problem sets into the training substantially enhances the problem-solving capability of language models across various mathematical domains. This study showcases the critical role of curated educational content in advancing AI research.- Anthology ID:
- 2024.mathnlp-1.4
- Volume:
- Proceedings of the 2nd Workshop on Mathematical Natural Language Processing @ LREC-COLING 2024
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Marco Valentino, Deborah Ferreira, Mokanarangan Thayaparan, Andre Freitas
- Venues:
- MathNLP | WS
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 25–34
- Language:
- URL:
- https://aclanthology.org/2024.mathnlp-1.4
- DOI:
- Cite (ACL):
- Byungju Kim, Wonseok Lee, Jaehong Kim, and Jungbin Im. 2024. Data Driven Approach for Mathematical Problem Solving. In Proceedings of the 2nd Workshop on Mathematical Natural Language Processing @ LREC-COLING 2024, pages 25–34, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Data Driven Approach for Mathematical Problem Solving (Kim et al., MathNLP-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2024.mathnlp-1.4.pdf