DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910645215035392 |
|---|---|
| author | Huang, Yiming Luo, Jianwen Yu, Yan Zhang, Yitong Lei, Fangyu Wei, Yifan He, Shizhu Huang, Lifu Liu, Xiao Zhao, Jun Liu, Kang |
| author_facet | Huang, Yiming Luo, Jianwen Yu, Yan Zhang, Yitong Lei, Fangyu Wei, Yifan He, Shizhu Huang, Lifu Liu, Xiao Zhao, Jun Liu, Kang |
| contents | We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them apart from traditional code generation tasks and demanding advanced coding skills in grounding and planning. Second, examples in DA-Code are all based on real and diverse data, covering a wide range of complex data wrangling and analytics tasks. Third, to solve the tasks, the models must utilize complex data science programming languages, to perform intricate data processing and derive the answers. We set up the benchmark in a controllable and executable environment that aligns with real-world data analysis scenarios and is scalable. The annotators meticulously design the evaluation suite to ensure the accuracy and robustness of the evaluation. We develop the DA-Agent baseline. Experiments show that although the baseline performs better than other existing frameworks, using the current best LLMs achieves only 30.5% accuracy, leaving ample room for improvement. We release our benchmark at https://da-code-bench.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07331 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models Huang, Yiming Luo, Jianwen Yu, Yan Zhang, Yitong Lei, Fangyu Wei, Yifan He, Shizhu Huang, Lifu Liu, Xiao Zhao, Jun Liu, Kang Computation and Language Artificial Intelligence We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them apart from traditional code generation tasks and demanding advanced coding skills in grounding and planning. Second, examples in DA-Code are all based on real and diverse data, covering a wide range of complex data wrangling and analytics tasks. Third, to solve the tasks, the models must utilize complex data science programming languages, to perform intricate data processing and derive the answers. We set up the benchmark in a controllable and executable environment that aligns with real-world data analysis scenarios and is scalable. The annotators meticulously design the evaluation suite to ensure the accuracy and robustness of the evaluation. We develop the DA-Agent baseline. Experiments show that although the baseline performs better than other existing frameworks, using the current best LLMs achieves only 30.5% accuracy, leaving ample room for improvement. We release our benchmark at https://da-code-bench.github.io. |
| title | DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.07331 |