代码大模型 / AI 编程

Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need!

Xiangxin Fang, Lev Mukhanov

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

Comments 13 pages, 8 figures

Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models

Jie Chen, Xintian Han, Yu Ma, Xun Zhou, Liang Xiang

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

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Martin Klissarov, Mikael Henaff, Roberta Raileanu, Shagun Sodhani, Pascal Vincent, Amy Zhang, Pierre-Luc Bacon, Doina Precup, Marlos C. Machado, Pierluca D'Oro

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

Combining Induction and Transduction for Abstract Reasoning

Wen-Ding Li, Keya Hu, Carter Larsen, Yuqing Wu, Simon Alford, Caleb Woo, Spencer M. Dunn, Hao Tang, Michelangelo Naim, Dat Nguyen, Wei-Long Zheng, Zenna Tavares, Yewen Pu, Kevin Ellis

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

PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing

Yiwen Duan, Yonghong Yu, Xiaoming Zhao, Yichang Wu, Wenbo Liu

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

Comments COLING-Industry 2025 accepted

Crystal: Illuminating LLM Abilities on Language and Code

Tianhua Tao, Junbo Li, Bowen Tan, Hongyi Wang, William Marshall, Bhargav M Kanakiya, Joel Hestness, Natalia Vassilieva, Zhiqiang Shen, Eric P. Xing, Zhengzhong Liu

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

Comments Published as a conference paper at COLM 2024

Efficacy of Various Large Language Models in Generating Smart Contracts

Siddhartha Chatterjee, Bina Ramamurthy

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

Comments 18 pages, accepted for presentation at 8th annual Future of Information and Communication Conference

Limits of Transformer Language Models on Learning to Compose Algorithms

Jonathan Thomm, Giacomo Camposampiero, Aleksandar Terzic, Michael Hersche, Bernhard Schölkopf, Abbas Rahimi

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

Comments NeurIPS 2024

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models

Jing Liu, Ruihao Gong, Mingyang Zhang, Yefei He, Jianfei Cai, Bohan Zhuang

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

Comments Tech report

B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests

Mouxiang Chen, Zhongxin Liu, He Tao, Yusu Hong, David Lo, Xin Xia, Jianling Sun

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

Comments accepted by ASE' 24 (full paper)

Investigating the Transferability of Code Repair for Low-Resource Programming Languages

Kyle Wong, Alfonso Amayuelas, Liangming Pan, William Yang Wang

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

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

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

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

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

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)

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)

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

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

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

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

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

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

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

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

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

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

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

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

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