Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset

Haoyi Wu, Wenyang Hui, Yezeng Chen, Weiqi Wu, Kewei Tu, Yi Zhou


Abstract
Mathematical understanding and reasoning are crucial tasks for assessing the capabilities of artificial intelligence (AI). However, existing benchmarks either require just a few steps of reasoning, or only contain a small amount of data in one specific topic, making it hard to analyse AI’s behaviour with reference to different problems within a specific topic in detail. In this work, we propose Conic10K, a challenging math problem dataset on conic sections in Chinese senior high school education. Our dataset contains various problems with different reasoning depths, while only the knowledge from conic sections is required. Since the dataset only involves a narrow range of knowledge, it is easy to separately analyse the knowledge a model possesses and the reasoning ability it has. For each problem, we provide a high-quality formal representation, the reasoning steps, and the final solution. Experiments show that existing large language models, including GPT-4, exhibit weak performance on complex reasoning. We hope that our findings could inspire more advanced techniques for precise natural language understanding and reasoning. Our dataset and codes are available at https://github.com/whyNLP/Conic10K.
Anthology ID:
2023.findings-emnlp.427
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6444–6458
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.427
DOI:
10.18653/v1/2023.findings-emnlp.427
Bibkey:
Cite (ACL):
Haoyi Wu, Wenyang Hui, Yezeng Chen, Weiqi Wu, Kewei Tu, and Yi Zhou. 2023. Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6444–6458, Singapore. Association for Computational Linguistics.
Cite (Informal):
Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset (Wu et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.427.pdf