代码大模型 / AI 编程 - arXivDaily 专题

2312.11511 2024-10-16 cs.CL cs.AI cs.LG 67%

ComplexityNet: Increasing LLM Inference Efficiency by Learning Task Complexity

Henry Bae, Aghyad Deeb, Alex Fleury, Kehang Zhu

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

2401.00757 2024-10-10 cs.SE cs.AI cs.CL cs.LO 67%

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models

Yuxuan Wan, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Jen-tse Huang, Pinjia He, Wenxiang Jiao, Michael R. Lyu

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

Comments Accepted by EMNLP 2024

2410.04707 2024-10-08 cs.LG cs.AI cs.CL 67%

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

Mehul Damani, Idan Shenfeld, Andi Peng, Andreea Bobu, Jacob Andreas

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

2410.03351 2024-10-07 cs.CL cs.PL cs.SE 67%

Generating Equivalent Representations of Code By A Self-Reflection Approach

Jia Li, Ge Li, Lecheng Wang, Hao Zhu, Zhi Jin

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

2311.00317 2024-10-07 cs.CL cs.LG cs.SE 67%

Data Augmentation for Code Translation with Comparable Corpora and Multiple References

Yiqing Xie, Atharva Naik, Daniel Fried, Carolyn Rose

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

Comments EMNLP 2023 Findings (with minor updates on the flowcharts)

2401.07870 2024-09-26 cs.CL cs.AI cs.SE 67%

JumpCoder: Go Beyond Autoregressive Coder via Online Modification

Mouxiang Chen, Hao Tian, Zhongxin Liu, Xiaoxue Ren, Jianling Sun

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

Comments ACL 2024 (main)

2409.16120 2024-09-25 cs.SE cs.AI cs.CL 67%

MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents

Ming Zhu, Yi Zhou

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

2409.15361 2024-09-25 cs.CL cs.AI cs.LG 67%

Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning

Essa Jan, Nouar AlDahoul, Moiz Ali, Faizan Ahmad, Fareed Zaffar, Yasir Zaki

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

Comments 19 pages, 11 figures

2409.13853 2024-09-24 cs.CL cs.AI cs.CR cs.LG 67%

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting

Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, Yanfu Zhang

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

2409.11411 2024-09-19 cs.AI cs.AR cs.CL cs.LG cs.MA 67%

AIvril: AI-Driven RTL Generation With Verification In-The-Loop

Mubashir ul Islam, Humza Sami, Pierre-Emmanuel Gaillardon, Valerio Tenace

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

2402.17988 2024-09-06 cs.PL cs.LG cs.SE 67%

Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars

Daniel Melcer, Nathan Fulton, Sanjay Krishna Gouda, Haifeng Qian

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

Comments 10 pages, Code available at https://github.com/amazon-science/incremental-parsing

2210.05506 2024-08-30 cs.SE cs.AI cs.HC cs.LG 67%

Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration

Matteo Paltenghi, Rahul Pandita, Austin Z. Henley, Albert Ziegler

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

Comments Published at IEEE Transactions on Software Engineering

2408.15866 2024-08-29 cs.SE cs.AI cs.LG 67%

Retrieval-Augmented Instruction Tuning for Automated Process Engineering Calculations : A Tool-Chaining Problem-Solving Framework with Attributable Reflection

Sagar Srinivas Sakhinana, Geethan Sannidhi, Venkataramana Runkana

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

Comments Accepted for publication at ML4CCE workshop at ECML PKDD 2024. Please find the link: https://ml4cce-ecml.com/#agenda

2408.14504 2024-08-28 cs.SE cs.AI cs.PL 67%

Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes

Heejae Chon, Seonghyeon Lee, Jinyoung Yeo, Dongha Lee

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

Comments 15pages, 6 figures, 8 tables

2408.08335 2024-08-19 cs.SE cs.AI cs.CL 67%

Plan with Code: Comparing approaches for robust NL to DSL generation

Nastaran Bassamzadeh, Chhaya Methani

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

Comments 9 pages, 1 figure, 5 tables. arXiv admin note: substantial text overlap with arXiv:2407.02742

2302.05319 2024-08-19 cs.CR cs.LG cs.PL cs.SE 67%

Large Language Models for Code: Security Hardening and Adversarial Testing

Jingxuan He, Martin Vechev

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

Comments Accepted to ACM CCS 2023

2402.06457 2024-08-15 cs.LG cs.AI cs.CL 67%

V-STaR: Training Verifiers for Self-Taught Reasoners

Arian Hosseini, Xingdi Yuan, Nikolay Malkin, Aaron Courville, Alessandro Sordoni, Rishabh Agarwal

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

2401.06461 2024-07-31 cs.SE cs.AI cs.CL 67%

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers

Yuling Shi, Hongyu Zhang, Chengcheng Wan, Xiaodong Gu

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

Comments Accepted by the 47th International Conference on Software Engineering (ICSE 2025). Code available at https://github.com/YerbaPage/DetectCodeGPT

2402.04858 2024-07-02 cs.AI cs.CL cs.LG 67%

CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay

Natasha Butt, Blazej Manczak, Auke Wiggers, Corrado Rainone, David W. Zhang, Michaël Defferrard, Taco Cohen

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

Comments ICML'24 camera-ready version

2406.18616 2024-06-28 cs.SE cs.AI cs.CL 67%

Towards Large Language Model Aided Program Refinement

Yufan Cai, Zhe Hou, Xiaokun Luan, David Miguel Sanan Baena, Yun Lin, Jun Sun, Jin Song Dong

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

2405.15729 2024-06-12 cs.SE cs.CL cs.LG 67%

Optimizing Large Language Models for OpenAPI Code Completion

Bohdan Petryshyn, Mantas Lukoševičius

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

Comments Update: a better quality and readability of figures, better explanation of code infilling and document splitting in training, some text polishing, making it more compact

2310.05492 2024-06-10 cs.CL cs.AI cs.LG 67%

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

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

Comments Accepted to ACL 2024 Main Conference

2312.14187 2024-06-10 cs.CL cs.AI cs.SE 67%

WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning

Zhaojian Yu, Xin Zhang, Ning Shang, Yangyu Huang, Can Xu, Yishujie Zhao, Wenxiang Hu, Qiufeng Yin

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

2401.04514 2024-06-04 cs.SE cs.CL cs.IR cs.LG 67%

Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search

Haochen Li, Xin Zhou, Zhiqi Shen

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

Comments Accepted to ACL 2024

2306.07856 2024-06-03 cs.AI cs.LG cs.SE 67%

Bayesian Program Learning by Decompiling Amortized Knowledge

Alessandro B. Palmarini, Christopher G. Lucas, N. Siddharth

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

2401.10314 2024-05-06 cs.SE cs.AI cs.LG cs.RO 67%

LangProp: A code optimization framework using Large Language Models applied to driving

Shu Ishida, Gianluca Corrado, George Fedoseev, Hudson Yeo, Lloyd Russell, Jamie Shotton, João F. Henriques, Anthony Hu

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

2404.10830 2024-05-03 cs.CL cs.AI cs.LG 67%

Fewer Truncations Improve Language Modeling

Hantian Ding, Zijian Wang, Giovanni Paolini, Varun Kumar, Anoop Deoras, Dan Roth, Stefano Soatto

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

Comments ICML 2024

2312.05677 2024-04-29 cs.LG cs.AI cs.CL 67%

Batched Low-Rank Adaptation of Foundation Models

Yeming Wen, Swarat Chaudhuri

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

Comments 16 pages, 3 figures

2403.03894 2024-04-16 cs.AI cs.CL cs.PL 67%

IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators

Indraneil Paul, Goran Glavaš, Iryna Gurevych

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

2404.08018 2024-04-15 cs.SE cs.AI cs.CL 67%

Analyzing the Performance of Large Language Models on Code Summarization

Rajarshi Haldar, Julia Hockenmaier

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

1. 代码生成 4092 篇

ComplexityNet: Increasing LLM Inference Efficiency by Learning Task Complexity

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

Generating Equivalent Representations of Code By A Self-Reflection Approach

Data Augmentation for Code Translation with Comparable Corpora and Multiple References

JumpCoder: Go Beyond Autoregressive Coder via Online Modification

MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents

Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting

AIvril: AI-Driven RTL Generation With Verification In-The-Loop

Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars

Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration

Retrieval-Augmented Instruction Tuning for Automated Process Engineering Calculations : A Tool-Chaining Problem-Solving Framework with Attributable Reflection

Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes

Plan with Code: Comparing approaches for robust NL to DSL generation

Large Language Models for Code: Security Hardening and Adversarial Testing

V-STaR: Training Verifiers for Self-Taught Reasoners

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers

CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay

Towards Large Language Model Aided Program Refinement

Optimizing Large Language Models for OpenAPI Code Completion

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning

Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search

Bayesian Program Learning by Decompiling Amortized Knowledge

LangProp: A code optimization framework using Large Language Models applied to driving

Fewer Truncations Improve Language Modeling

Batched Low-Rank Adaptation of Foundation Models

IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators

Analyzing the Performance of Large Language Models on Code Summarization