English
Related papers

Related papers: CursorCore: Assist Programming through Aligning An…

200 papers

Large language models (LLMs) can often generate functionally correct code, but their ability to produce efficient implementations for performance-critical systems tasks remains limited. Existing code benchmarks mainly emphasize correctness…

Software Engineering · Computer Science 2026-05-18 Huihao Jing , Wenbin Hu , Haochen Shi , Hanyu Yang , Sirui Zhang , Shaojin Chen , Haoran Li , Yangqiu Song

The transition from sequential to parallel computing is essential for modern high-performance applications but is hindered by the steep learning curve of concurrent programming. This challenge is magnified for irregular data structures…

Machine Learning · Computer Science 2026-03-04 Liu Yang , Zeyu Nie , Andrew Liu , Felix Zou , Deniz Altinbüken , Amir Yazdanbakhsh , Quanquan C. Liu

Despite recent advances in AI, the development of systems capable of executing complex, multi-step reasoning tasks involving multiple tools remains a significant challenge. Current benchmarks fall short in capturing the real-world…

Computation and Language · Computer Science 2025-01-03 Vaskar Nath , Pranav Raja , Claire Yoon , Sean Hendryx

Novice programmers benefit from timely, personalized support that addresses individual learning gaps, yet the availability of instructors and teaching assistants is inherently limited. Large language models (LLMs) present opportunities to…

Computers and Society · Computer Science 2025-10-07 Griffin Pitts , Anurata Prabha Hridi , Arun-Balajiee Lekshmi-Narayanan

Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation…

Computation and Language · Computer Science 2025-07-01 José Pombal , Sweta Agrawal , Patrick Fernandes , Emmanouil Zaranis , André F. T. Martins

Textual content is often the output of a collaborative writing process: We start with an initial draft, ask for suggestions, and repeatedly make changes. Agnostic of this process, today's language models are trained to generate only the…

State-of-the-art large language models (LLMs) have demonstrated impressive code generation capabilities but struggle with real-world software engineering tasks, such as revising source code to address code reviews, hindering their practical…

Software Engineering · Computer Science 2025-06-03 Hong Yi Lin , Chunhua Liu , Haoyu Gao , Patanamon Thongtanunam , Christoph Treude

Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely…

While Large Language Models (LLMs) have demonstrated remarkable capabilities, research shows that their effectiveness depends not only on explicit prompts but also on the broader context provided. This requirement is especially pronounced…

Software Engineering · Computer Science 2026-03-05 Shaokang Jiang , Daye Nam

The mismatch between the growing demand for psychological counseling and the limited availability of services has motivated research into the application of Large Language Models (LLMs) in this domain. Consequently, there is a need for a…

Computation and Language · Computer Science 2025-11-13 Bichen Wang , Yixin Sun , Junzhe Wang , Hao Yang , Xing Fu , Yanyan Zhao , Si Wei , Shijin Wang , Bing Qin

Recent advances in machine learning have significantly improved the understanding of source code data and achieved good performance on a number of downstream tasks. Open source repositories like GitHub enable this process with rich…

Software Engineering · Computer Science 2022-06-20 Ming Zhu , Aneesh Jain , Karthik Suresh , Roshan Ravindran , Sindhu Tipirneni , Chandan K. Reddy

In this work, we introduce CodeRepoQA, a large-scale benchmark specifically designed for evaluating repository-level question-answering capabilities in the field of software engineering. CodeRepoQA encompasses five programming languages and…

Software Engineering · Computer Science 2024-12-20 Ruida Hu , Chao Peng , Jingyi Ren , Bo Jiang , Xiangxin Meng , Qinyun Wu , Pengfei Gao , Xinchen Wang , Cuiyun Gao

Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…

Computation and Language · Computer Science 2019-05-30 Woon Sang Cho , Pengchuan Zhang , Yizhe Zhang , Xiujun Li , Michel Galley , Chris Brockett , Mengdi Wang , Jianfeng Gao

Software testing is a critical aspect of software development, yet generating test cases remains a routine task for engineers. This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and completing test cases…

Software Engineering · Computer Science 2025-02-14 Jiacheng Xu , Bo Pang , Jin Qu , Hiroaki Hayashi , Caiming Xiong , Yingbo Zhou

There has recently been growing interest in the automatic generation of cooking recipes that satisfy some form of dietary restrictions, thanks in part to the availability of online recipe data. Prior studies have used pre-trained language…

Computation and Language · Computer Science 2023-01-27 Diego Antognini , Shuyang Li , Boi Faltings , Julian McAuley

Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to…

Software Engineering · Computer Science 2026-04-21 Duy Tung Doan , Quang Huy Phung , Dzung Nguyen , Khac-Hoai Nam Bui

Think-Aloud Computing, a method for capturing users' verbalized thoughts during software tasks, allows eliciting rich contextual insights into evolving intentions, struggles, and decision-making processes of users in real-time. However,…

Human-Computer Interaction · Computer Science 2026-02-11 Frederic Gmeiner , John Thompson , George Fitzmaurice , Justin Matejka

Multimodal scene search of conversations is essential for unlocking valuable insights into social dynamics and enhancing our communication. While experts in conversational analysis have their own knowledge and skills to find key scenes, a…

Human-Computer Interaction · Computer Science 2024-02-20 Riku Arakawa , Kiyosu Maeda , Hiromu Yakura

We examine "vibe coding": an emerging programming paradigm where developers primarily write code by interacting with code-generating large language models rather than writing code directly. We present the first empirical study of vibe…

Human-Computer Interaction · Computer Science 2025-10-06 Advait Sarkar , Ian Drosos

Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation, the task of transforming informal into formal mathematical statements. Autoformalisation helps…

Computation and Language · Computer Science 2025-10-15 Yupei Li , Philipp Borchert , Gerasimos Lampouras