Suchergebnisse - "LLMs for coding tasks"

A Catalog of Data Smells for Coding Tasks

Autoren: Antonio Vitale Rocco Oliveto Simone Scalabrino

Quelle: ACM Transactions on Software Engineering and Methodology. 34:1-32

Schlagwörter: data quality, data smells, LLMs for coding tasks, Systematic Literature Review, 0202 electrical engineering, electronic engineering, information engineering, LMs for coding tasks, 02 engineering and technology

Dateibeschreibung: application/pdf

Black-Box Reconstruction Attacks on LLMs: A Preliminary Study in Code Summarization

Autoren: Russodivito M. Spina A. Scalabrino S. et al.

Quelle: Communications in Computer and Information Science ISBN: 9783031702440

Schlagwörter: LLMs for Coding Tasks, Reconstruction Attacks, Security

Zugangs-URL: https://hdl.handle.net/11695/150233
https://doi.org/10.1007/978-3-031-70245-7_27

A Catalog of Data Smells for Coding Tasks.

Autoren: Vitale, Antonio Oliveto, Rocco Scalabrino, Simone

Quelle: ACM Transactions on Software Engineering & Methodology; May2025, Vol. 34 Issue 4, p1-32, 32p

Schlagwörter: LANGUAGE models, COMPUTER software development, DATA integrity, DATA quality, TAXONOMY

Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index.

Autoren: Christakis, Nicholas Drikakis, Dimitris

Quelle: Applied Sciences (2076-3417); Apr2025, Vol. 15 Issue 7, p3784, 24p

Schlagwörter: LANGUAGE models, LONG short-term memory, ARTIFICIAL intelligence, GENERATIVE pre-trained transformers, WIND speed

Should we still teach or learn coding? A postgraduate student perspective on the use of large language models for coding in ecology and evolution.

Autoren: Campbell, Heather Bluck, Thomas Curry, Ella et al.

Quelle: Methods in Ecology & Evolution; Oct2024, Vol. 15 Issue 10, p1767-1770, 4p

Schlagwörter: LANGUAGE models, STUDENT attitudes, LEARNING curve, ARTIFICIAL intelligence, CHATGPT

Code LLMs: A Taxonomy-based Survey

Autoren: Raihan, Nishat Newman, Christian Zampieri, Marcos

Index Begriffe: Computer Science - Computation and Language, text

URL: http://arxiv.org/abs/2412.08291

Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights

Autoren: Krishna, Rahul Pan, Rangeet Pavuluri, Raju et al.

Index Begriffe: Computer Science - Software Engineering, text

URL: http://arxiv.org/abs/2410.13007

Decoding Complexity: Exploring Human-AI Concordance in Qualitative Coding

Autoren: Kirsten, Elisabeth Buckmann, Annalina Mhaidli, Abraham et al.

Index Begriffe: Computer Science - Human-Computer Interaction, text

URL: http://arxiv.org/abs/2403.06607

Pharmacometrics in the Age of Large Language Models: A Vision of the Future.

Autoren: Tosca, Elena Maria Aiello, Ludovica De Carlo, Alessandro et al.

Quelle: Pharmaceutics; Oct2025, Vol. 17 Issue 10, p1274, 26p

Schlagwörter: LANGUAGE models, ARTIFICIAL intelligence, PREDICTION models, DIGITAL twin, PHARMACOLOGY, ELECTRONIC data processing, DRUG development

Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights

Autoren: Rahul Krishna Rangeet Pan Saurabh Sinha et al.

Quelle: Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering. :308-318

Schlagwörter: Software Engineering (cs.SE), FOS: Computer and information sciences, Computer Science - Software Engineering

Zugangs-URL: http://arxiv.org/abs/2410.13007

How Programming Concepts and Neurons Are Shared in Code Language Models

Autoren: Kargaran, Amir Hossein Liu, Yihong Yvon, François et al.

Weitere Verfasser: Kargaran, Amir Hossein Liu, Yihong Yvon, François et al.

Quelle: Findings of the Association for Computational Linguistics: ACL 2025. :26905-26917

Schlagwörter: Software Engineering (cs.SE), FOS: Computer and information sciences, Computer Science - Software Engineering, Computer Science - Computation and Language, Computer Science - Programming Languages, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Computation and Language (cs.CL), Programming Languages (cs.PL)

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2506.01074

From Data to Deployment: A Comprehensive Analysis of Risks in Large Language Model Research and Development.

Autoren: Zhang, Tianshu Su, Ruidan Zhong, Anli et al.

Quelle: IET Information Security (Wiley-Blackwell); 6/23/2025, Vol. 2025, p1-13, 13p

Schlagwörter: LANGUAGE models, INFORMATION processing, RESEARCH personnel, LANGUAGE research, RISK assessment

Impact of Developer Queries on the Effectiveness of Conversational Large Language Models in Programming.

Autoren: Taneski, Viktor Karakatič, Sašo Rek, Patrik et al.

Quelle: Applied Sciences (2076-3417); Jun2025, Vol. 15 Issue 12, p6836, 22p

Schlagwörter: LANGUAGE models, ARTIFICIAL intelligence, COLLOQUIAL language, COMPUTER software development, EDUCATIONAL planning

A Systematic Survey on Large Language Models for Static Code Analysis.

Autoren: Mohammed Salih, Hekar A. Sarhan, Qusay I.

Quelle: ARO: The Scientific Journal of Koya University; 2025, Vol. 13 Issue 1, p251-265, 15p

Schlagwörter: LANGUAGE models, ARTIFICIAL intelligence, SOFTWARE measurement, COMPUTER software quality control, EVIDENCE gaps

Should we still teach or learn coding? A postgraduate student perspective on the use of large language models for coding in ecology and evolution

Autoren: Heather Campbell Thomas Bluck Ella Curry et al.

Quelle: Methods in Ecology and Evolution, Vol 15, Iss 10, Pp 1767-1770 (2024)

Schlagwörter: coding, education, ChatGPT, Ecology, Evolution, QH359-425, large language models, artificial intelligence, teaching, QH540-549.5

Zugangs-URL: https://doaj.org/article/f550b7ecc0f0498d9e1dd93e49668ab9

Do Code Models Suffer from the Dunning-Kruger Effect?

Autoren: Singh, Mukul Chatterjee, Somya Radhakrishna, Arjun et al.

Schlagwörter: Artificial Intelligence, Computation and Language, Software Engineering

Relation: http://arxiv.org/abs/2510.05457

Verfügbarkeit: http://arxiv.org/abs/2510.05457

Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index

Autoren: Nicholas Christakis Dimitris Drikakis

Quelle: Applied Sciences ; Volume 15 ; Issue 7 ; Pages: 3784

Schlagwörter: LLM, forecasting, inference, time series, LSTM, artificial intelligence

Geographisches Schlagwort: agris

Dateibeschreibung: application/pdf

Relation: Computing and Artificial Intelligence; https://dx.doi.org/10.3390/app15073784

Verfügbarkeit: https://doi.org/10.3390/app15073784

Assessing the effectiveness of recent closed-source large language models in fault localization and automated program repair.

Autoren: Wang, Bo Deng, Ming Chen, Mingda et al.

Quelle: Automated Software Engineering; Jun2026, Vol. 33 Issue 1, p1-42, 42p

Output format biases in the evaluation of large language models for code translation.

Autoren: Macedo, Marcos Tian, Yuan Cogo, Filipe R. et al.

Quelle: Empirical Software Engineering; Apr2026, Vol. 31 Issue 2, p1-35, 35p

OpenCodeReasoning: Advancing Data Distillation for Competitive Coding

Autoren: Ahmad, Wasi Uddin Narenthiran, Sean Majumdar, Somshubra et al.

Schlagwörter: FOS: Computer and information sciences, Computation and Language, Computation and Language (cs.CL)

Zugangs-URL: http://arxiv.org/abs/2504.01943