English
Related papers

Related papers: CrossCodeEval: A Diverse and Multilingual Benchmar…

200 papers

Large Language Models (LLMs) are predominantly assessed based on their common sense reasoning, language comprehension, and logical reasoning abilities. While models trained in specialized domains like mathematics or coding have demonstrated…

Software Engineering · Computer Science 2026-01-08 Danny Brahman , Mohammad Mahoor

Despite the recent advances showing that a model pre-trained on large-scale source code data is able to gain appreciable generalization capability, it still requires a sizeable amount of data on the target task for fine-tuning. And the…

Software Engineering · Computer Science 2023-02-13 Changan Niu , Chuanyi Li , Vincent Ng , Bin Luo

Large language models (LLMs) have manifested strong ability to generate codes for productive activities. However, current benchmarks for code synthesis, such as HumanEval, MBPP, and DS-1000, are predominantly oriented towards introductory…

Computation and Language · Computer Science 2024-05-08 Shudan Zhang , Hanlin Zhao , Xiao Liu , Qinkai Zheng , Zehan Qi , Xiaotao Gu , Xiaohan Zhang , Yuxiao Dong , Jie Tang

We present CRUXEval (Code Reasoning, Understanding, and eXecution Evaluation), a benchmark consisting of 800 Python functions (3-13 lines). Each function comes with an input-output pair, leading to two natural tasks: input prediction and…

Software Engineering · Computer Science 2024-01-09 Alex Gu , Baptiste Rozière , Hugh Leather , Armando Solar-Lezama , Gabriel Synnaeve , Sida I. Wang

Transformer-based language models for automatic code completion have shown great promise so far, yet the evaluation of these models rarely uses real data. This study provides both quantitative and qualitative assessments of three public…

Software Engineering · Computer Science 2024-02-27 Maliheh Izadi , Jonathan Katzy , Tim van Dam , Marc Otten , Razvan Mihai Popescu , Arie van Deursen

Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial models such as Codex, CodeGen, and PanGu-Coder. To evaluate the…

Software Engineering · Computer Science 2024-02-26 Hao Yu , Bo Shen , Dezhi Ran , Jiaxin Zhang , Qi Zhang , Yuchi Ma , Guangtai Liang , Ying Li , Qianxiang Wang , Tao Xie

Code large language models (Code LLMs) have made significant progress in code generation by translating natural language descriptions into functional code; however, real-world applications often demand stricter adherence to detailed…

Computation and Language · Computer Science 2025-08-04 Jian Yang , Wei Zhang , Shukai Liu , Linzheng Chai , Yingshui Tan , Jiaheng Liu , Ge Zhang , Wangchunshu Zhou , Guanglin Niu , Zhoujun Li , Binyuan Hui , Junyang Lin

Retrieval-augmented generation (RAG) has recently demonstrated considerable potential for repository-level code completion, as it integrates cross-file knowledge with in-file preceding code to provide comprehensive contexts for generation.…

Software Engineering · Computer Science 2025-08-11 Yanzhou Li , Shangqing Liu , Kangjie Chen , Tianwei Zhang , Yang Liu

Large Language models have achieved impressive performance in automated software engineering. Extensive efforts have been made to evaluate the abilities of code LLMs in various aspects, with an increasing number of benchmarks and evaluation…

Software Engineering · Computer Science 2025-03-25 Lezhi Ma , Shangqing Liu , Lei Bu , Shangru Li , Yida Wang , Yang Liu

Evaluating the performance of Code Language Models (CLMs) for software engineering tasks, especially in multilingual and low-resource programming language settings, poses significant challenges. These challenges are primarily due to the…

Software Engineering · Computer Science 2024-11-26 Rohit Dandamudi , Gema Rodríguez-Pérez

Large Language Models (LLMs) have demonstrated remarkable performance on assisting humans in programming and facilitating programming automation. However, existing benchmarks for evaluating the code understanding and generation capacities…

Computation and Language · Computer Science 2024-06-10 Weixiang Yan , Haitian Liu , Yunkun Wang , Yunzhe Li , Qian Chen , Wen Wang , Tingyu Lin , Weishan Zhao , Li Zhu , Hari Sundaram , Shuiguang Deng

Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However, current benchmarks primarily exercise LLMs' capability on…

Artificial Intelligence · Computer Science 2024-08-26 Qiming Zhu , Jialun Cao , Yaojie Lu , Hongyu Lin , Xianpei Han , Le Sun , Shing-Chi Cheung

Recent advances in machine learning have significantly improved the understanding of source code data and achieved good performance on a number of downstream tasks. Open source repositories like GitHub enable this process with rich…

Software Engineering · Computer Science 2022-06-20 Ming Zhu , Aneesh Jain , Karthik Suresh , Roshan Ravindran , Sindhu Tipirneni , Chandan K. Reddy

The complexity of modern software has led to a drastic increase in the time and cost associated with detecting and rectifying software bugs. In response, researchers have explored various methods to automatically generate fixes for buggy…

Software Engineering · Computer Science 2023-03-31 Md Mahim Anjum Haque , Wasi Uddin Ahmad , Ismini Lourentzou , Chris Brown

Existing code generation benchmarks for Large Language Models (LLMs) such as HumanEval and MBPP are designed to study LLMs' end-to-end performance, where the benchmarks feed a problem description in natural language as input and examine the…

Software Engineering · Computer Science 2025-02-27 Jiarong Wu , Songqiang Chen , Jialun Cao , Hau Ching Lo , Shing-Chi Cheung

Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intelligent completion tools evolve, we need a robust evaluation…

Software Engineering · Computer Science 2024-10-25 Zhenyu Pan , Rongyu Cao , Yongchang Cao , Yingwei Ma , Binhua Li , Fei Huang , Han Liu , Yongbin Li

The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit…

Software Engineering · Computer Science 2024-09-16 Wei Liu , Ailun Yu , Daoguang Zan , Bo Shen , Wei Zhang , Haiyan Zhao , Zhi Jin , Qianxiang Wang

Recent code translation techniques exploit neural machine translation models to translate source code from one programming language to another to satisfy production compatibility or to improve efficiency of codebase maintenance. Most…

Artificial Intelligence · Computer Science 2023-10-26 Weixiang Yan , Yuchen Tian , Yunzhe Li , Qian Chen , Wen Wang

Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. However, existing LLM-based code completion systems primarily…

Software Engineering · Computer Science 2024-12-12 Zhanming Guan , Junlin Liu , Jierui Liu , Chao Peng , Dexin Liu , Ningyuan Sun , Bo Jiang , Wenchao Li , Jie Liu , Hang Zhu

Large language models are increasingly becoming a popular tool for software development. Their ability to model and generate source code has been demonstrated in a variety of contexts, including code completion, summarization, translation,…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-15 Daniel Nichols , Joshua H. Davis , Zhaojun Xie , Arjun Rajaram , Abhinav Bhatele