English
Related papers

Related papers: Learning Syntactic Program Transformations from Ex…

200 papers

Underlying data distributions of natural language, programming code, and mathematical symbols vary vastly, presenting a complex challenge for large language models (LLMs) that strive to achieve high performance across all three domains…

Computation and Language · Computer Science 2024-03-27 Ning Ding , Yulin Chen , Ganqu Cui , Xingtai Lv , Weilin Zhao , Ruobing Xie , Bowen Zhou , Zhiyuan Liu , Maosong Sun

While large language models (LLMs) now excel at code generation, a key aspect of software development is the art of refactoring: consolidating code into libraries of reusable and readable programs. In this paper, we introduce LILO, a…

Computation and Language · Computer Science 2024-03-18 Gabriel Grand , Lionel Wong , Maddy Bowers , Theo X. Olausson , Muxin Liu , Joshua B. Tenenbaum , Jacob Andreas

Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…

Computation and Language · Computer Science 2025-03-18 Zezhong Wang , Xingshan Zeng , Weiwen Liu , Liangyou Li , Yasheng Wang , Lifeng Shang , Xin Jiang , Qun Liu , Kam-Fai Wong

Detecting semantic interference remains a challenge in collaborative software development. Recent lightweight static analysis techniques improve efficiency over SDG-based methods, but they still suffer from a high rate of false positives. A…

Software Engineering · Computer Science 2025-10-03 Victor Lira , Paulo Borba , Rodrigo Bonifácio , Galileu Santos e Matheus barbosa

Refactoring is a common practice in software development, aimed at improving the internal code structure in order to make it easier to understand and modify. Consequently, it is often assumed that refactoring makes the code less prone to…

Software Engineering · Computer Science 2025-05-14 Isabella Ferreira , Lawrence Arkoh , Anderson Uchôa , Ana Carla Bibiano , Alessandro Garcia , Wesley K. G. Assunção

Instruction tuning plays a pivotal role in Code Large Language Models (Code LLMs) for the task of program synthesis. Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct…

Computation and Language · Computer Science 2024-03-04 Xianzhen Luo , Qingfu Zhu , Zhiming Zhang , Xu Wang , Qing Yang , Dongliang Xu , Wanxiang Che

Language models for program synthesis are usually trained and evaluated on programming competition datasets (MBPP, APPS). However, these datasets are limited in size and quality, while these language models are extremely data hungry.…

Software Engineering · Computer Science 2025-07-23 Noah van der Vleuten

Human mathematicians are often good at recognizing modular and reusable theorems that make complex mathematical results within reach. In this paper, we propose a novel method called theoREm-from-prooF extrACTOR (REFACTOR) for training…

Artificial Intelligence · Computer Science 2024-02-28 Jin Peng Zhou , Yuhuai Wu , Qiyang Li , Roger Grosse

Data synthesis for training large reasoning models offers a scalable alternative to limited, human-curated datasets, enabling the creation of high-quality data. However, existing approaches face several challenges: (i) indiscriminate…

Artificial Intelligence · Computer Science 2026-05-11 Yongxian Wei , Yilin Zhao , Zixuan Hu , Li Shen , Xinrui Chen , Runxi Cheng , Sinan Du , Hao Yu , Chun Yuan , Dian Li

Code completion is a prominent application of Large Language Models (LLMs) in software engineering. Due to the near real-time response requirements of this task, base models with small to medium-sized parameters are typically employed,…

Software Engineering · Computer Science 2025-09-18 Dongjun Yu , Xiao Yan , Zhenrui Li , Jipeng Xiao , Haochuan He , Yongda Yu , Hao Zhang , Guoping Rong , Xiaobo Huang

Chart visualizations are essential for data interpretation and communication; however, most charts are only accessible in image format and lack the corresponding data tables and supplementary information, making it difficult to alter their…

Computer Vision and Pattern Recognition · Computer Science 2024-05-02 Pengyu Yan , Mahesh Bhosale , Jay Lal , Bikhyat Adhikari , David Doermann

In the task of automatic program synthesis, one obtains pairs of matching inputs and outputs and generates a computer program, in a particular domain-specific language (DSL), which given each sample input returns the matching output. A key…

Machine Learning · Computer Science 2023-03-14 Aran Carmon , Lior Wolf

This paper presents a study of using large language models (LLMs) in modifying existing code. While LLMs for generating code have been widely studied, their role in code modification remains less understood. Although "prompting" serves as…

Software Engineering · Computer Science 2025-08-05 Ningzhi Tang , Emory Smith , Yu Huang , Collin McMillan , Toby Jia-Jun Li

Compiling programs to an instruction set architecture (ISA) requires a set of rewrite rules that map patterns consisting of compiler instructions to patterns consisting of ISA instructions. We synthesize such rules by constructing SMT…

Logic in Computer Science · Computer Science 2024-05-21 Ross Daly , Caleb Donovick , Caleb Terrill , Jackson Melchert , Priyanka Raina , Clark Barrett , Pat Hanrahan

Large language models (LLMs) often exhibit flawed reasoning ability that undermines reliability. Existing approaches to improving reasoning typically treat it as a general and monolithic skill, applying broad training which is inefficient…

Computation and Language · Computer Science 2026-03-10 Zhenyu Lei , Qiong Wu , Jianxiong Dong , Yinhan He , Emily Dodwell , Yushun Dong , Jundong Li

Recent advancements in large pre-trained transformer models (GPT2/3, T5) have found use in program synthesis to generate programs that satisfy a set of input/output examples. However, these models perform poorly on long-horizon and low-data…

Programming Languages · Computer Science 2022-05-20 Jack Roper

Errors in data are usually unwelcome and so some means to correct them is useful. However, it is difficult to define, detect or correct errors in an unsupervised way. Here, we train a deep neural network to re-synthesize its inputs at its…

Machine Learning · Computer Science 2015-02-17 Andrew J. R. Simpson

Many software systems today face uncertain operating conditions, such as sudden changes in the availability of resources or unexpected user behavior. Without proper mitigation these uncertainties can jeopardize the system goals.…

Software Engineering · Computer Science 2023-12-14 Danny Weyns , Omid Gheibi , Federico Quin , Jeroen Van Der Donckt

Although some recent works show potential complementarity among different state-of-the-art systems, few works try to investigate this problem in text summarization. Researchers in other areas commonly refer to the techniques of reranking or…

Computation and Language · Computer Science 2021-04-16 Yixin Liu , Zi-Yi Dou , Pengfei Liu

We present a new approach to example-guided program synthesis based on counterexample-guided abstraction refinement. Our method uses the abstract semantics of the underlying DSL to find a program $P$ whose abstract behavior satisfies the…

Programming Languages · Computer Science 2017-10-24 Xinyu Wang , Isil Dillig , Rishabh Singh