English
Related papers

Related papers: When Correct Isn't Usable: Improving Structured Ou…

200 papers

Large Language Models (LLMs) have rapidly transformed software development, especially in code generation. However, their inconsistent performance, prone to hallucinations and quality issues, complicates program comprehension and hinders…

Software Engineering · Computer Science 2025-04-21 Antonio Della Porta , Stefano Lambiase , Fabio Palomba

This case study investigates the task of job classification in a real-world setting, where the goal is to determine whether an English-language job posting is appropriate for a graduate or entry-level position. We explore multiple…

Computation and Language · Computer Science 2023-04-19 Benjamin Clavié , Alexandru Ciceu , Frederick Naylor , Guillaume Soulié , Thomas Brightwell

Prompt engineering is a challenging yet crucial task for optimizing the performance of large language models on customized tasks. It requires complex reasoning to examine the model's errors, hypothesize what is missing or misleading in the…

Computation and Language · Computer Science 2024-07-04 Qinyuan Ye , Maxamed Axmed , Reid Pryzant , Fereshte Khani

In the area of code generation research, the emphasis has transitioned from crafting individual functions to developing class-level method code that integrates contextual information. This shift has brought several benchmarks such as…

Software Engineering · Computer Science 2024-08-28 Zinan Wang

Existing LMs struggle with proof-oriented programming due to data scarcity, which manifest in two key ways: (1) a lack of sufficient corpora for proof-oriented programming languages such as F*, and (2) the absence of large-scale,…

Computation and Language · Computer Science 2025-04-15 Dylan Zhang , Justin Wang , Tianran Sun

AI coding assistants are now used to generate production code in security-sensitive domains, yet the exploitability of their outputs remains unquantified. We address this gap with Broken by Default: a formal verification study of 3,500 code…

Cryptography and Security · Computer Science 2026-04-09 Dominik Blain , Maxime Noiseux

Designing a computational imaging system -- selecting operators, setting parameters, validating consistency -- requires weeks of specialist effort per modality, creating an expertise bottleneck that excludes the broader scientific community…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Chengshuai Yang

Recent advances in large language models (LLMs) have driven extensive evaluations in software engineering. however, most prior work concentrates on code-level tasks, leaving software design capabilities underexplored. To fill this gap, we…

Software Engineering · Computer Science 2026-03-12 Bingxu Xiao , Yunwei Dong , Yiqi Tang , Manqing Zhang , Yifan Zhou , Chunyan Ma , Yepang Liu

Large language models can generate scientific simulation code, but the generated code silently fails on most non-textbook problems. We show that classical mathematical validation -- well-posedness, convergence, and error certification --…

Software Engineering · Computer Science 2026-03-30 Chengshuai Yang

This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how…

Artificial Intelligence · Computer Science 2025-04-04 Giannis Chatziveroglou , Richard Yun , Maura Kelleher

The use of Large Language Models (LLMs) in software development is rapidly growing, with developers increasingly relying on these models for coding assistance, including security-critical tasks. Our work presents a comprehensive comparison…

Cryptography and Security · Computer Science 2024-11-18 Zohaib Masood , Miguel Vargas Martin

Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This paper targets on-device and low-cost small language model (SLM) deployments, where…

Machine Learning · Computer Science 2026-05-27 Jaideep Ray

We introduce MetaGlyph, a symbolic language for compressing prompts by encoding instructions as mathematical symbols rather than prose. Unlike systems requiring explicit decoding rules, MetaGlyph uses symbols like $\in$ (membership) and…

Computation and Language · Computer Science 2026-01-13 Ernst van Gassen

Artificially intelligent (AI) co-scientists must be able to sift through research literature cost-efficiently while applying nuanced scientific reasoning. We evaluate Small Language Models (SLMs, <= 8B parameters) for classifying medical…

Computational Engineering, Finance, and Science · Computer Science 2025-12-09 Muhammed Muaaz Dawood , Mohammad Zaid Moonsamy , Kaela Kokkas , Hairong Wang , Robert F. Breiman , Richard Klein , Emmanuel K. Sekyi , Bruce A. Bassett

Large Language Models (LLMs) are trained on massive amounts of data, enabling their application across diverse domains and tasks. Despite their remarkable performance, most LLMs are developed and evaluated primarily in English. Recently, a…

Computation and Language · Computer Science 2024-10-18 Krishno Dey , Prerona Tarannum , Md. Arid Hasan , Imran Razzak , Usman Naseem

AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with formal architecture descriptors can reduce this navigational overhead. We present three…

Software Engineering · Computer Science 2026-04-16 Ruoqi Jin

Large language models (LLMs) have shown promise for scientific data extraction from publications, but rely on manual prompt refinement. We present an expert-grounded automatic prompt optimization framework that enhances LLM entity…

Digital Libraries · Computer Science 2025-12-30 Shunshun Liu , Talon R. Booth , Yangfeng Ji , Wesley Reinhart , Prasanna V. Balachandran

This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially…

Computation and Language · Computer Science 2022-02-10 Jason Wei , Maarten Bosma , Vincent Y. Zhao , Kelvin Guu , Adams Wei Yu , Brian Lester , Nan Du , Andrew M. Dai , Quoc V. Le

Multimodal large language models (MLLMs) hold considerable promise for applications in healthcare. However, their deployment in safety-critical settings is hindered by two key limitations: (i) sensitivity to prompt design, and (ii) a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Anita Kriz , Elizabeth Laura Janes , Xing Shen , Tal Arbel

Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often overlook the long tail topics and rely on popular repositories…