Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2025

Abstract

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for this http URL assess how well LLMs can solve challenging and practical tasks via programs, we introduce BigCodeBench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. To evaluate LLMs rigorously, each task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area.

Keywords

Code Generation, Tool Use, Instruction Following, Benchmark, Software engineering, Artificial Intelligence

Discipline

Artificial Intelligence and Robotics | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

Proceedings of the International Conference on Learning Representations, ICLR 2025: Singapore, April 24-28

First Page

99488

Last Page

99542

ISBN

9798331320850

Publisher

International Conference on Learning Representations, ICLR

City or Country

Singapore

Comments

Zhuo, T.Y.; Vu, M.C.; Chim, J.; Hu H.; Yu W.; Widyasari R.; Yusuf I.N.B.; Zhan H.; He J.; Paul I.; Brunner S.; Gong C.; Hoang T.; Zebaze A.; Hong X.; Li W.D.; Kaddour J.; Xu M.; Zhang Z.; Yadav P.; Jain N.; Gu A.; Cheng Z.; Liu J.; Liu Q.; Wang Z.; Hui B.; Muennighoff N.; Lo D.; Fried D.; Du X.; de Vries H.; von Werra L.

Additional URL

https://openreview.net/pdf?id=YrycTjllL0

Download

Share

COinS