CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs’ Mathematical Reasoning Capabilities

Yujun Mao, Yoon Kim, Yilun Zhou


Abstract
Recent large language models (LLMs) have shown indications of mathematical reasoning ability on challenging competition-level problems, especially with self-generated verbalizations of intermediate reasoning steps (i.e., chain-of-thought prompting). However, current evaluations mainly focus on the end-to-end final answer correctness, and it is unclear whether LLMs can make use of helpful side information such as problem-specific hints. In this paper, we propose a challenging benchmark dataset for enabling such analyses. The Concept and Hint-Annotated Math Problems (CHAMP) consists of high school math competition problems, annotated with concepts, or general math facts, and hints, or problem-specific tricks. These annotations allow us to explore the effects of additional information, such as relevant hints, misleading concepts, or related problems. This benchmark is difficult, with the best model only scoring 58.1% in standard settings. With concepts and hints, performance sometimes improves, indicating that some models can make use of such side information. Furthermore, we annotate model-generated solutions for their correctness. Using this corpus, we find that models often arrive at the correct final answer through wrong reasoning steps. In addition, we test whether models are able to verify these solutions, and find that most models struggle.
Anthology ID:
2024.findings-acl.785
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13256–13274
Language:
URL:
https://aclanthology.org/2024.findings-acl.785
DOI:
10.18653/v1/2024.findings-acl.785
Bibkey:
Cite (ACL):
Yujun Mao, Yoon Kim, and Yilun Zhou. 2024. CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs’ Mathematical Reasoning Capabilities. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13256–13274, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs’ Mathematical Reasoning Capabilities (Mao et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-acl.785.pdf