ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models
Yanan Wu, Jie Liu, Xingyuan Bu, Jiaheng Liu, Zhanhui Zhou, Yuanxing Zhang, Chenchen Zhang, ZhiqiBai ZhiqiBai, Haibin Chen, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Bo Zheng
Abstract
This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs). Unlike traditional benchmarks that evaluate general mathematical reasoning with an average accuracy, ConceptMath systemically organizes math problems under a hierarchy of math concepts, so that mathematical reasoning can be evaluated at different granularity with concept-wise accuracies. Based on our ConcepthMath, we then evaluate a broad range of LLMs, and we observe existing LLMs, though achieving high average accuracies on traditional benchmarks, exhibit significant performance variations across different math concepts and may even fail catastrophically on the most basic ones. Besides, we also introduce an efficient fine-tuning strategy to enhance the weaknesses of existing LLMs. Finally, we hope ConceptMath could guide the developers to understand the fine-grained mathematical abilities of their models and facilitate the growth of foundation models. Code is available at https://github.com/conceptmath/conceptmath.- Anthology ID:
- 2024.findings-acl.407
- Volume:
- Findings of the Association for Computational Linguistics ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand and virtual meeting
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6815–6839
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.407
- DOI:
- Cite (ACL):
- Yanan Wu, Jie Liu, Xingyuan Bu, Jiaheng Liu, Zhanhui Zhou, Yuanxing Zhang, Chenchen Zhang, ZhiqiBai ZhiqiBai, Haibin Chen, Tiezheng Ge, Wanli Ouyang, Wenbo Su, and Bo Zheng. 2024. ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models. In Findings of the Association for Computational Linguistics ACL 2024, pages 6815–6839, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models (Wu et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.407.pdf