ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909343936413696 |
|---|---|
| author | Waghjale, Siddhant Veerendranath, Vishruth Wang, Zora Zhiruo Fried, Daniel |
| author_facet | Waghjale, Siddhant Veerendranath, Vishruth Wang, Zora Zhiruo Fried, Daniel |
| contents | Although large language models (LLMs) have been largely successful in generating functionally correct programs, conditioning models to produce efficient solutions while ensuring correctness remains a challenge. Further, unreliability in benchmarking code efficiency is a hurdle across varying hardware specifications for popular interpreted languages such as Python. In this paper, we present ECCO, a reproducible benchmark for evaluating program efficiency via two paradigms: natural language (NL) based code generation and history-based code editing. On ECCO, we adapt and thoroughly investigate the three most promising existing LLM-based approaches: in-context learning, iterative refinement with execution or NL feedback, and fine-tuning conditioned on execution and editing history. While most methods degrade functional correctness and moderately increase program efficiency, we find that adding execution information often helps maintain functional correctness, and NL feedback enhances more on efficiency. We release our benchmark to support future work on LLM-based generation of efficient code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14044 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness? Waghjale, Siddhant Veerendranath, Vishruth Wang, Zora Zhiruo Fried, Daniel Computation and Language Artificial Intelligence Although large language models (LLMs) have been largely successful in generating functionally correct programs, conditioning models to produce efficient solutions while ensuring correctness remains a challenge. Further, unreliability in benchmarking code efficiency is a hurdle across varying hardware specifications for popular interpreted languages such as Python. In this paper, we present ECCO, a reproducible benchmark for evaluating program efficiency via two paradigms: natural language (NL) based code generation and history-based code editing. On ECCO, we adapt and thoroughly investigate the three most promising existing LLM-based approaches: in-context learning, iterative refinement with execution or NL feedback, and fine-tuning conditioned on execution and editing history. While most methods degrade functional correctness and moderately increase program efficiency, we find that adding execution information often helps maintain functional correctness, and NL feedback enhances more on efficiency. We release our benchmark to support future work on LLM-based generation of efficient code. |
| title | ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness? |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.14044 |