paper-with-me

Papers

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

2024-07-19 · Siddhant Waghjale, Vishruth Veerendranath, Zora Zhiruo Wang, Daniel Fried

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.

📄 PDF Abstract BibTeX arXiv:2407.14044

Code (2)

codeeff/ecco 공식 구현
judge0/judge0

Tasks

BenchmarkingCode GenerationIn-Context Learning

Similar Papers 제목 키워드 기반

SecCodeBench-V2 Technical Report

2026-02-17 · Longfei Chen, Ji Zhao, Lanxiao Cui, Tong Su 외 arxiv

We introduce SecCodeBench-V2, a publicly released benchmark for evaluating Large Language Model (LLM) copilots' capabilities of generating secure code. SecCodeBench-V2 comprises 98 generation and fix scenarios derived fr…

AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code

2026-05-18 · Shangzhan Li, Xinyu Yin, Xuanyu Jin, Ye He 외 arxiv

Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resort to explicit vectorization using intrin…

Reinforcement LearningCode Generation

Functional and Secure Code Generation with Task Vectors

2026-07-08 · Felix Wang, Anudeep Das, Mei Nagappan, N. Asokan arxiv

Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security vulnerabilities. Prior work to improve the secure code generation abilities of such c…

Code Generation

RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations

2024-12-27 · Mingshu Zhao, Yi Luo, Yong Ouyang

Recent advances in vision transformers (ViTs) have demonstrated the advantage of global modeling capabilities, prompting widespread integration of large-kernel convolutions for enlarging the effective receptive field (ER…

Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights

2023-10-21 · Carmel Fiscko, Aayushya Agarwal, Yihan Ruan, Soummya Kar 외

We present a stochastic first-order optimization method specialized for deep neural networks (DNNs), ECCO-DNN. This method models the optimization variable trajectory as a dynamical system and develops a discretization a…

Numerical Integration