代码大模型 / AI 编程 - arXivDaily 专题

2501.17584 2025-01-30 cs.SE cs.CL cs.LG 82%

GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback

Mohamed Abdelaal, Samuel Lokadjaja, Gilbert Engert

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.LG

Journal ref Industrial Track of 21st Conference on Database Systems for Business, Technology and Web (BTW), 2025

2402.14658 2025-01-08 cs.SE cs.AI cs.CL 82%

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

Tianyu Zheng, Ge Zhang, Tianhao Shen, Xueling Liu, Bill Yuchen Lin, Jie Fu, Wenhu Chen, Xiang Yue

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

2501.02138 2025-01-07 cs.PL cs.AI cs.SE 82%

Effective LLM-Driven Code Generation with Pythoness

Kyla H. Levin, Kyle Gwilt, Emery D. Berger, Stephen N. Freund

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.AI、cs.PL

Comments 5 pages

2308.10462 2024-12-30 cs.SE cs.CL cs.LG 82%

Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models

Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari Sahraoui

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.LG

2412.17330 2024-12-24 cs.LG cs.AI cs.PL 82%

EcoSearch: A Constant-Delay Best-First Search Algorithm for Program Synthesis

Théo Matricon, Nathanaël Fijalkow, Guillaume Lagarde

专题命中代码生成：program synthesis(title,abstract)；分类 cs.AI、cs.LG、cs.PL

Comments Extended version of AAAI 2025

2412.12447 2024-12-23 cs.SE cs.AI cs.CL 82%

PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation

Jaeseok Yoo, Hojae Han, Youngwon Lee, Jaejin Kim, Seung-won Hwang

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments Accepted by COLING 2025 main conference

2411.15470 2024-11-26 cs.SE cs.AI cs.PL 82%

A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks

Rohit Dandamudi, Gema Rodríguez-Pérez

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.AI、cs.PL

Comments 5 pages, ASEW 2024

Journal ref ASEW 2024: Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering Workshops, Pages 94 - 99

2312.05356 2024-11-21 cs.SE cs.CL cs.LG 82%

Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation

Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.LG

Comments 13 pages, 7 figures, 7 tables, under peer-review

2411.10861 2024-11-19 cs.LG cs.AI cs.SE 82%

See-Saw Generative Mechanism for Scalable Recursive Code Generation with Generative AI

Ruslan Idelfonso Magaña Vsevolodovna

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.AI、cs.LG

Comments 18 pages, 4 figures

2411.10753 2024-11-19 cs.SE cs.AI cs.CL 82%

Chain-of-Programming (CoP) : Empowering Large Language Models for Geospatial Code Generation

Shuyang Hou, Haoyue Jiao, Zhangxiao Shen, Jianyuan Liang, Anqi Zhao, Xiaopu Zhang, Jianxun Wang, Huayi Wu

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

2310.17807 2024-11-19 cs.AI cs.LG cs.SE 82%

Clover: Closed-Loop Verifiable Code Generation

Chuyue Sun, Ying Sheng, Oded Padon, Clark Barrett

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.AI、cs.LG

Comments add appendix

2410.15966 2024-10-22 cs.CL cs.AI cs.SE 82%

Self-Explained Keywords Empower Large Language Models for Code Generation

Lishui Fan, Mouxiang Chen, Zhongxin Liu

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

2403.13583 2024-10-15 cs.SE cs.CL cs.LG 82%

CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing

Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian Yuan, Dongmei Zhang

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.LG

Comments Accepted by EMNLP 2024 main conference, long paper

2407.11470 2024-10-10 cs.SE cs.AI cs.CL 82%

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models

Jiasheng Zheng, Boxi Cao, Zhengzhao Ma, Ruotong Pan, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments We release benchmark at https://github.com/jszheng21/RACE and leaderboard at https://huggingface.co/spaces/jszheng/RACE_leaderboard

2410.02184 2024-10-04 cs.LG cs.CL cs.SE 82%

CodeJudge: Evaluating Code Generation with Large Language Models

Weixi Tong, Tianyi Zhang

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.LG

Comments Accepted to EMNLP 2024 (Main, Long Paper)

2410.00558 2024-10-02 cs.CL cs.AI cs.SE 82%

AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation

Ziyang Luo, Xin Li, Hongzhan Lin, Jing Ma, Lidong Bing

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments EMNLP 2024

2409.15228 2024-09-27 cs.SE cs.AI cs.LG 82%

A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models

Yixi Wu, Pengfei He, Zehao Wang, Shaowei Wang, Yuan Tian, Tse-Hsun Chen

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.AI、cs.LG

2409.13928 2024-09-24 cs.SE cs.AI cs.CL 82%

Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation

Seonghyeon Lee, Suyeon Kim, Joonwon Jang, Heejae Chon, Dongha Lee, Hwanjo Yu

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments EMNLP 2024 Findings Short

2409.12020 2024-09-19 cs.SE cs.AI cs.LG 82%

Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization

Zhi Chen, Lingxiao Jiang

专题命中代码生成：code generation(title)；code model(abstract)；分类 cs.SE、cs.AI、cs.LG

Comments Paper accepted to the ASE 2024 Conference Research Track

2405.17514 2024-09-13 cs.SE cs.AI cs.PL 82%

AbstractBeam: Enhancing Bottom-Up Program Synthesis using Library Learning

Janis Zenkner, Lukas Dierkes, Tobias Sesterhenn, Chrisitan Bartelt

专题命中代码生成：program synthesis(title,abstract)；分类 cs.SE、cs.AI、cs.PL

2409.04164 2024-09-09 cs.CL cs.LG cs.SE 82%

Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation

Luis Mayer, Christian Heumann, Matthias Aßenmacher

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.LG

Comments Conference Paper accepted at the 9th SwissText Conference (2024)

2408.06450 2024-08-14 cs.SE cs.CL cs.LG 82%

Evaluating Language Models for Efficient Code Generation

Jiawei Liu, Songrun Xie, Junhao Wang, Yuxiang Wei, Yifeng Ding, Lingming Zhang

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.LG

2311.03366 2024-08-09 cs.SE cs.AI cs.LG 82%

Functional Overlap Reranking for Neural Code Generation

Hung Quoc To, Minh Huynh Nguyen, Nghi D. Q. Bui

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.AI、cs.LG

Comments ACL 2024, Long Findings

2408.00994 2024-08-05 cs.SE cs.AI cs.CL 82%

ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models

Hojae Han, Jaejin Kim, Jaeseok Yoo, Youngwon Lee, Seung-won Hwang

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments Accepted by ACL 2024 main conference

2405.00218 2024-07-23 cs.CR cs.AI cs.LG cs.SE 82%

Constrained Decoding for Secure Code Generation

Yanjun Fu, Ethan Baker, Yu Ding, Yizheng Chen

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.AI、cs.LG

Comments 17 pages, 9 figures, our website is available at https://codeguardplus.github.io

2407.02742 2024-07-04 cs.SE cs.AI cs.CL 82%

A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation

Nastaran Bassamzadeh, Chhaya Methani

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments 8 pages, 1 figure

2406.11925 2024-07-04 cs.SE cs.AI cs.CL 82%

DocCGen: Document-based Controlled Code Generation

Sameer Pimparkhede, Mehant Kammakomati, Srikanth Tamilselvam, Prince Kumar, Ashok Pon Kumar, Pushpak Bhattacharyya

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

2401.03003 2024-06-25 cs.SE cs.CL cs.LG 82%

AST-T5: Structure-Aware Pretraining for Code Generation and Understanding

Linyuan Gong, Mostafa Elhoushi, Alvin Cheung

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.LG

Comments 15 pages; ICML 2024: https://icml.cc/virtual/2024/poster/33601

2406.04379 2024-06-10 cs.SE cs.AI cs.CL 82%

VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation

Prashanth Vijayaraghavan, Luyao Shi, Stefano Ambrogio, Charles Mackin, Apoorva Nitsure, David Beymer, Ehsan Degan

专题命中代码生成：code generation(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments 6 pages, 3 Figures, LAD'24

2312.02120 2024-06-10 cs.CL cs.AI cs.SE 82%

Magicoder: Empowering Code Generation with OSS-Instruct

Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, Lingming Zhang

专题命中代码生成：code generation(title)；code model(abstract)；分类 cs.SE、cs.CL、cs.AI

Comments Published at ICML 2024

1. 代码生成 4102 篇

GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

Effective LLM-Driven Code Generation with Pythoness

Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models

EcoSearch: A Constant-Delay Best-First Search Algorithm for Program Synthesis

PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation

A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks

Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation

See-Saw Generative Mechanism for Scalable Recursive Code Generation with Generative AI

Chain-of-Programming (CoP) : Empowering Large Language Models for Geospatial Code Generation

Clover: Closed-Loop Verifiable Code Generation

Self-Explained Keywords Empower Large Language Models for Code Generation

CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models

CodeJudge: Evaluating Code Generation with Large Language Models

AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation

A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models

Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation

Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization

AbstractBeam: Enhancing Bottom-Up Program Synthesis using Library Learning

Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation

Evaluating Language Models for Efficient Code Generation

Functional Overlap Reranking for Neural Code Generation

ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models

Constrained Decoding for Secure Code Generation

A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation

DocCGen: Document-based Controlled Code Generation

AST-T5: Structure-Aware Pretraining for Code Generation and Understanding

VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation

Magicoder: Empowering Code Generation with OSS-Instruct