English
Related papers

Related papers: Can Program Synthesis be Used to Learn Merge Confl…

200 papers

We present a high-level domain-specific language (DSL) interface to drive an adaptive incomplete $k$-d tree-based framework for finite element (FEM) solutions to PDEs. This DSL provides three key advances: (a) it abstracts out the…

Computational Engineering, Finance, and Science · Computer Science 2023-06-01 Eric Heisler , Cheng-Hau Yang , Aadesh Deshmukh , Baskar Ganapathysubramanian , Hari Sundar

Data reconciliation in general, and filesystem synchronization in particular, lacks rigorous theoretical foundation. This paper presents, for the first time, a complete analysis of synchronization for two replicas of a theoretical…

Information Theory · Computer Science 2022-11-15 Elod P. Csirmaz , Laszlo Csirmaz

The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code…

Software Engineering · Computer Science 2025-06-04 Zixiang Xian , Chenhui Cui , Rubing Huang , Chunrong Fang , Zhenyu Chen

Large language models (LLMs) have become vital tools for software development, but they often require verbose intermediate reasoning for complex code tasks, leading to high latency and costs. This research extends the Chain of Draft (CoD)…

Software Engineering · Computer Science 2025-06-16 Shaoyi Yang

Iteratively improving and repairing source code with large language models (LLMs), known as refinement, has emerged as a popular way of generating programs that would be too complex to construct in one shot. Given a bank of test cases,…

Software Engineering · Computer Science 2024-10-31 Hao Tang , Keya Hu , Jin Peng Zhou , Sicheng Zhong , Wei-Long Zheng , Xujie Si , Kevin Ellis

Source code spends most of its time in a broken or incomplete state during software development. This presents a challenge to machine learning for code, since high-performing models typically rely on graph structured representations of…

Machine Learning · Computer Science 2021-06-01 Xuechen Li , Chris J. Maddison , Daniel Tarlow

The goal of program synthesis is to automatically generate programs in a particular language from corresponding specifications, e.g. input-output behavior. Many current approaches achieve impressive results after training on randomly…

Machine Learning · Computer Science 2020-01-01 Richard Shin , Neel Kant , Kavi Gupta , Christopher Bender , Brandon Trabucco , Rishabh Singh , Dawn Song

The rapid evolution of software libraries creates a significant challenge for Large Language Models (LLMs), whose static parametric knowledge often becomes stale post-training. While retrieval-augmented generation (RAG) is commonly used to…

Software Engineering · Computer Science 2026-04-13 Ahmed Nusayer Ashik , Shaowei Wang , Tse-Hsun Chen , Muhammad Asaduzzaman , Yuan Tian

Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential…

Artificial Intelligence · Computer Science 2026-05-26 Qiming Bao , Xiaoxuan Fu , Michael Witbrock

Large language models (LLMs) often need to balance their internal parametric knowledge with external information, such as user beliefs and content from retrieved documents, in real-world scenarios like RAG or chat-based systems. A model's…

Computation and Language · Computer Science 2026-04-27 Shuowei Li , Haoxin Li , Wenda Chu , Yi Fang

Current benchmarks for coding evaluate language models (LMs) on concrete, well-specified tasks such as fixing specific bugs or writing targeted tests. However, human programmers do not spend all day incessantly addressing isolated tasks.…

Software Engineering · Computer Science 2026-05-14 John Yang , Kilian Lieret , Joyce Yang , Carlos E. Jimenez , Muhtasham Oblokulov , Aryan Siddiqui , Ofir Press , Ludwig Schmidt , Diyi Yang

Large language models (LLMs) have shown impressive performance on general-purpose tasks, yet adapting them to specific domains remains challenging due to the scarcity of high-quality domain data. Existing data synthesis tools often struggle…

Computation and Language · Computer Science 2025-07-08 Ziyang Miao , Qiyu Sun , Jingyuan Wang , Yuchen Gong , Yaowei Zheng , Shiqi Li , Richong Zhang

Regular expressions (regexes) are a powerful mechanism for solving string-matching problems. They are supported by all modern programming languages, and have been estimated to appear in more than a third of Python and JavaScript projects.…

Software Engineering · Computer Science 2023-03-07 Louis G. Michael , James Donohue , James C. Davis , Dongyoon Lee , Francisco Servant

Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA, where high-quality parallel data…

Programming Languages · Computer Science 2025-12-04 Le Chen , Nuo Xu , Winson Chen , Bin Lei , Pei-Hung Lin , Dunzhi Zhou , Rajeev Thakur , Caiwen Ding , Ali Jannesari , Chunhua Liao

In today's society, we are becoming increasingly dependent on software systems. However, we also constantly witness the negative impacts of buggy software. Program synthesis aims to improve software correctness by automatically generating…

Software Engineering · Computer Science 2023-12-11 Sanyogita Piya , Allison Sullivan

Fine-tuning pre-trained Large Language Models (LLMs) for specialized tasks incurs substantial computational and data costs. While model merging offers a training-free solution to integrate multiple task-specific models, existing methods…

Computation and Language · Computer Science 2025-08-15 Qianli Ma , Dongrui Liu , Qian Chen , Linfeng Zhang , Jing Shao

Large Language Models (LLMs) are essential for analyzing and addressing vulnerabilities in cybersecurity. However, among over 200,000 vulnerabilities were discovered in the past decade, more than 30,000 have been changed or updated. This…

Computation and Language · Computer Science 2026-04-17 Ziyin Zhou , Jianyi Zhang , Xu ji , Yilong Li , Jiameng Han , Zhangchi Zhao

During the software evolution, existing features may be adversely affected by new changes, which is well known as regression errors. Maintaining a high-quality test suite is helpful to prevent regression errors, whereas it heavily depends…

Software Engineering · Computer Science 2020-09-23 Tao Ji , Liqian Chen , Xiaoguang Mao , Xin Yi , Jiahong Jiang

Large Language Models (LLMs) have been increasingly used to optimize code efficiency. Evaluating their effectiveness and further suggesting optimization opportunities often rely on high-quality tests to demonstrate the performance…

Software Engineering · Computer Science 2025-12-08 Jun Yang , Cheng-Chi Wang , Bogdan Alexandru Stoica , Kexin Pei

Today's pursuit of a single Large Language Model (LMM) for all software engineering tasks is resource-intensive and overlooks the potential benefits of complementarity, where different models contribute unique strengths. However, the degree…

Software Engineering · Computer Science 2025-10-31 Fernando Vallecillos-Ruiz , Max Hort , Leon Moonen
‹ Prev 1 3 4 5 6 7 10 Next ›