paper-with-me

Papers

DevEval: Evaluating Code Generation in Practical Software Projects

2024-01-12 · Jia Li, Ge Li, YunFei Zhao, Yongmin Li, Zhi Jin, Hao Zhu, Huanyu Liu, Kaibo Liu, Lecheng Wang, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yihong Dong, Yuqi Zhu, Bin Gu, Mengfei Yang

How to evaluate Large Language Models (LLMs) in code generation is an open question. Many benchmarks have been proposed but are inconsistent with practical software projects, e.g., unreal program distributions, insufficient dependencies, and small-scale project contexts. Thus, the capabilities of LLMs in practical projects are still unclear. In this paper, we propose a new benchmark named DevEval, aligned with Developers' experiences in practical projects. DevEval is collected through a rigorous pipeline, containing 2,690 samples from 119 practical projects and covering 10 domains. Compared to previous benchmarks, DevEval aligns to practical projects in multiple dimensions, e.g., real program distributions, sufficient dependencies, and enough-scale project contexts. We assess five popular LLMs on DevEval (e.g., gpt-4, gpt-3.5-turbo, CodeLLaMa, and StarCoder) and reveal their actual abilities in code generation. For instance, the highest Pass@1 of gpt-3.5-turbo only is 42 in our experiments. We also discuss the challenges and future directions of code generation in practical projects. We open-source DevEval and hope it can facilitate the development of code generation in practical projects.

📄 PDF Abstract BibTeX arXiv:2401.06401

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study

2024-03-13 · Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi 외

Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities. However, existing benchmarks predominantly focused on simplified or isolated aspects of coding, such as single-fi…

Code Generation

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories

2024-05-30 · Jia Li, Ge Li, YunFei Zhao, Yongmin Li 외

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the co…

Code Generation

Can Language Models Replace Programmers for Coding? REPOCOD Says 'Not Yet'

2024-10-29 · Shanchao Liang, Yiran Hu, Nan Jiang, Lin Tan

Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have emerged to evaluate the capabilities of large language models (LLMs) beyond standa…

Code CompletionCode GenerationHumanEvalmbpp+1

CodeAlchemy: Synthetic Code Rewriting at Scale

2026-06-08 · Ankit Gupta, Aditya Prasad, Rameswar Panda arxiv

Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats. While synthetic data has proven transformative for language models, code remains largely unexplored beyond limited q…

Synthetic Data Generation

When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding

2026-05-31 · Xu Yang, Lunyiu Nie, Ethan Chandra, Stanislav Gannutin 외 arxiv

Multi-agent Large Language Model (LLM) systems offer a way to decompose complex tasks, such as coding, through parallelization and context isolation. However, adding agents in practice introduces inter-agent communicatio…

Community Detectiongraph partitioning