SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models

Xiaoxuan Wang, Ziniu Hu, Pan Lu, Yanqiao Zhu, Jieyu Zhang, Satyen Subramaniam, Arjun R Loomba, Shichang Zhang, Yizhou Sun, Wei Wang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50622-50649, 2024.

Abstract

Most existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capabilities required for solving complex scientific problems, we introduce an expansive benchmark suite SciBench for LLMs. SciBench contains a carefully curated dataset featuring a range of collegiate-level scientific problems from mathematics, chemistry, and physics domains. Based on the dataset, we conduct an in-depth benchmarking study of representative open-source and proprietary LLMs with various prompting strategies. The results reveal that current LLMs fall short of delivering satisfactory performance, with the best overall score of merely 43.22%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms the others and some strategies that demonstrate improvements in certain problem-solving skills could result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-wang24z, title = {{S}ci{B}ench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models}, author = {Wang, Xiaoxuan and Hu, Ziniu and Lu, Pan and Zhu, Yanqiao and Zhang, Jieyu and Subramaniam, Satyen and Loomba, Arjun R and Zhang, Shichang and Sun, Yizhou and Wang, Wei}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {50622--50649}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/wang24z/wang24z.pdf}, url = {https://proceedings.mlr.press/v235/wang24z.html}, abstract = {Most existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capabilities required for solving complex scientific problems, we introduce an expansive benchmark suite SciBench for LLMs. SciBench contains a carefully curated dataset featuring a range of collegiate-level scientific problems from mathematics, chemistry, and physics domains. Based on the dataset, we conduct an in-depth benchmarking study of representative open-source and proprietary LLMs with various prompting strategies. The results reveal that current LLMs fall short of delivering satisfactory performance, with the best overall score of merely 43.22%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms the others and some strategies that demonstrate improvements in certain problem-solving skills could result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery.} }
Endnote
%0 Conference Paper %T SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models %A Xiaoxuan Wang %A Ziniu Hu %A Pan Lu %A Yanqiao Zhu %A Jieyu Zhang %A Satyen Subramaniam %A Arjun R Loomba %A Shichang Zhang %A Yizhou Sun %A Wei Wang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-wang24z %I PMLR %P 50622--50649 %U https://proceedings.mlr.press/v235/wang24z.html %V 235 %X Most existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capabilities required for solving complex scientific problems, we introduce an expansive benchmark suite SciBench for LLMs. SciBench contains a carefully curated dataset featuring a range of collegiate-level scientific problems from mathematics, chemistry, and physics domains. Based on the dataset, we conduct an in-depth benchmarking study of representative open-source and proprietary LLMs with various prompting strategies. The results reveal that current LLMs fall short of delivering satisfactory performance, with the best overall score of merely 43.22%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms the others and some strategies that demonstrate improvements in certain problem-solving skills could result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery.
APA
Wang, X., Hu, Z., Lu, P., Zhu, Y., Zhang, J., Subramaniam, S., Loomba, A.R., Zhang, S., Sun, Y. & Wang, W.. (2024). SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:50622-50649 Available from https://proceedings.mlr.press/v235/wang24z.html.

Related Material