跳到正文
arXiv cs.AI· Terry Yue Zhuo, Minh Chien Vu, Jenny Chim, Han Hu, Wenhao Yu, Ratnadira Widyasari, Imam Nur Bani Yusuf, Haolan Zhan, Junda He, Indraneil Paul, Simon Brunner, Chen Gong, Thong Hoang, Armel Randy Zebaze, Xiaoheng Hong, Wen-Ding Li, Jean Kaddour, Ming Xu, Zhihan Zhang, Prateek Yadav, Naman Jain, Alex Gu, Zhoujun Cheng, Jiawei Liu, Qian Liu, Zijian Wang, Binyuan Hui, Niklas Muennighoff, David Lo, Daniel Fried, Xiaoning Du, Harm de Vries, Leandro Von Werra·· 4 小时前AI 评分34

BigCodeBench:用多样函数调用与复杂指令评测大语言模型代码生成

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

AI 导读

BigCodeBench 基准挑战大语言模型在 1,140 个细粒度任务中调用来自 139 个库、7 个领域的多个函数,平均每个任务含 5.6 个测试用例、分支覆盖率达 99%。对 60 个 LLM 的评估显示,模型得分最高仅 60%,远低于人类的 97%,表明模型尚不能精确遵循复杂指令使用函数调用。

正文 · 原文

Authors:Terry Yue Zhuo, Minh Chien Vu, Jenny Chim, Han Hu, Wenhao Yu, Ratnadira Widyasari, Imam Nur Bani Yusuf, Haolan Zhan, Junda He, Indraneil Paul, Simon Brunner, Chen Gong, Thong Hoang, Armel Randy Zebaze, Xiaoheng Hong, Wen-Ding Li, Jean Kaddour, Ming Xu, Zhihan Zhang, Prateek Yadav, Naman Jain, Alex Gu, Zhoujun Cheng, Jiawei Liu, Qian Liu, Zijian Wang, Binyuan Hui, Niklas Muennighoff, David Lo, Daniel Fried, Xiaoning Du, Harm de Vries, Leandro Von Werra

View PDF HTML (experimental)

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.
Comments: Accpeted at ICLR 2025 (Oral), built with love by the BigCode community :)
Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2406.15877 [cs.SE]
  (or arXiv:2406.15877v5 [cs.SE] for this version)
  https://doi.org/10.48550/arXiv.2406.15877

arXiv-issued DOI via DataCite

Submission history

From: Terry Yue Zhuo [view email]
[v1] Sat, 22 Jun 2024 15:52:04 UTC (1,396 KB)
[v2] Wed, 26 Jun 2024 17:05:14 UTC (1,393 KB)
[v3] Mon, 7 Oct 2024 17:23:30 UTC (2,662 KB)
[v4] Tue, 1 Apr 2025 08:36:44 UTC (2,650 KB)
[v5] Fri, 13 Nov 2026 11:41:39 UTC (2,030 KB)

来源:arXiv cs.AI · arxiv.org