ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?

Siddhant Waghjale, Vishruth Veerendranath, Zhiruo Wang, Daniel Fried


Abstract
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.
Anthology ID:
2024.emnlp-main.859
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15362–15376
Language:
URL:
https://aclanthology.org/2024.emnlp-main.859
DOI:
10.18653/v1/2024.emnlp-main.859
Bibkey:
Cite (ACL):
Siddhant Waghjale, Vishruth Veerendranath, Zhiruo Wang, and Daniel Fried. 2024. ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15362–15376, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness? (Waghjale et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.859.pdf
Data:
 2024.emnlp-main.859.data.zip