Exploring and evaluating hallucinations in llm-powered code generation

Transformers in source code generation: A comprehensive survey

H Ghaemi, Z Alizadehsani, A Shahraki… - Journal of Systems …, 2024 - Elsevier
Transformers have revolutionized natural language processing (NLP) and have had a huge
impact on automating tasks. Recently, transformers have led to the development of powerful …
相关文章
[PDF] arxiv.org

Exploring and unleashing the power of large language models in automated code translation

Z Yang, F Liu, Z Yu, JW Keung, J Li, S Liu… - arXiv preprint arXiv …, 2024 - arxiv.org
Code translation tools are developed for automatic source-to-source translation. Although
learning-based transpilers have shown impressive enhancement against rule-based …
被引用次数：2 相关文章 所有 2 个版本
[PDF] arxiv.org

Multi-Modal and Multi-Agent Systems Meet Rationality: A Survey

B Jiang, Y Xie, X Wang, WJ Su, CJ Taylor… - arXiv preprint arXiv …, 2024 - arxiv.org
Rationality is the quality of being guided by reason, characterized by logical thinking and
decision-making that align with evidence and logical rules. This quality is essential for …
被引用次数：1 相关文章 所有 2 个版本

SimAC: simulating agile collaboration to generate acceptance criteria in user story elaboration

Y Li, J Keung, Z Yang, X Ma, J Zhang, S Liu - Automated Software …, 2024 - Springer
In agile requirements engineering, Generating Acceptance Criteria (GAC) to elaborate user
stories plays a pivotal role in the sprint planning phase, which provides a reference for …
相关文章 所有 2 个版本
[PDF] arxiv.org

An Empirical Study of Unit Test Generation with Large Language Models

L Yang, C Yang, S Gao, W Wang, B Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Unit testing is an essential activity in software development for verifying the correctness of
software components. However, manually writing unit tests is challenging and time …
相关文章
[PDF] arxiv.org

Security of AI Agents

Y He, E Wang, Y Rong, Z Cheng, H Chen - arXiv preprint arXiv …, 2024 - arxiv.org
The study and development of AI agents have been boosted by large language models. AI
agents can function as intelligent assistants and complete tasks on behalf of their users with …
相关文章 所有 2 个版本
[PDF] arxiv.org

We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs

J Spracklen, R Wijewickrama, AHM Sakib… - arXiv preprint arXiv …, 2024 - arxiv.org
The reliance of popular programming languages such as Python and JavaScript on
centralized package repositories and open-source software, combined with the emergence …
相关文章
[PDF] arxiv.org

How and Why LLMs Use Deprecated APIs in Code Completion? An Empirical Study

C Wang, K Huang, J Zhang, Y Feng, L Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs), pre-trained or fine-tuned on large code corpora, have
shown effectiveness in generating code completions. However, in LLM-based code …
相关文章
[PDF] arxiv.org

Identifying Performance-Sensitive Configurations in Software Systems through Code Analysis with LLM Agents

Z Wang, DJ Kim, TH Chen - arXiv preprint arXiv:2406.12806, 2024 - arxiv.org
Configuration settings are essential for tailoring software behavior to meet specific
performance requirements. However, incorrect configurations are widespread, and …
相关文章
[PDF] arxiv.org

The Role of Code Proficiency in the Era of Generative AI

G Robles, C Treude, JM Gonzalez-Barahona… - arXiv preprint arXiv …, 2024 - arxiv.org
At the current pace of technological advancements, Generative AI models, including both
Large Language Models and Large Multi-modal Models, are becoming integral to the …
相关文章 所有 2 个版本