SENAI: Towards Software Engineering Native Generative Artificial Intelligence

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Saad, Mootez, López, José Antonio Hernández, Chen, Boqi, Ernst, Neil, Varró, Dániel, Sharma, Tushar
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917961801924608
author Saad, Mootez
López, José Antonio Hernández
Chen, Boqi
Ernst, Neil
Varró, Dániel
Sharma, Tushar
author_facet Saad, Mootez
López, José Antonio Hernández
Chen, Boqi
Ernst, Neil
Varró, Dániel
Sharma, Tushar
contents Large Language Models have significantly advanced the field of code generation, demonstrating the ability to produce functionally correct code snippets. However, advancements in generative AI for code overlook foundational Software Engineering (SE) principles such as modularity, and single responsibility, and concepts such as cohesion and coupling which are critical for creating maintainable, scalable, and robust software systems. These concepts are missing in pipelines that start with pre-training and end with the evaluation using benchmarks. This vision paper argues for the integration of SE knowledge into LLMs to enhance their capability to understand, analyze, and generate code and other SE artifacts following established SE knowledge. The aim is to propose a new direction where LLMs can move beyond mere functional accuracy to perform generative tasks that require adherence to SE principles and best practices. In addition, given the interactive nature of these conversational models, we propose using Bloom's Taxonomy as a framework to assess the extent to which they internalize SE knowledge. The proposed evaluation framework offers a sound and more comprehensive evaluation technique compared to existing approaches such as linear probing. Software engineering native generative models will not only overcome the shortcomings present in current models but also pave the way for the next generation of generative models capable of handling real-world software engineering.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15282
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SENAI: Towards Software Engineering Native Generative Artificial Intelligence
Saad, Mootez
López, José Antonio Hernández
Chen, Boqi
Ernst, Neil
Varró, Dániel
Sharma, Tushar
Software Engineering
Large Language Models have significantly advanced the field of code generation, demonstrating the ability to produce functionally correct code snippets. However, advancements in generative AI for code overlook foundational Software Engineering (SE) principles such as modularity, and single responsibility, and concepts such as cohesion and coupling which are critical for creating maintainable, scalable, and robust software systems. These concepts are missing in pipelines that start with pre-training and end with the evaluation using benchmarks. This vision paper argues for the integration of SE knowledge into LLMs to enhance their capability to understand, analyze, and generate code and other SE artifacts following established SE knowledge. The aim is to propose a new direction where LLMs can move beyond mere functional accuracy to perform generative tasks that require adherence to SE principles and best practices. In addition, given the interactive nature of these conversational models, we propose using Bloom's Taxonomy as a framework to assess the extent to which they internalize SE knowledge. The proposed evaluation framework offers a sound and more comprehensive evaluation technique compared to existing approaches such as linear probing. Software engineering native generative models will not only overcome the shortcomings present in current models but also pave the way for the next generation of generative models capable of handling real-world software engineering.
title SENAI: Towards Software Engineering Native Generative Artificial Intelligence
topic Software Engineering
url https://arxiv.org/abs/2503.15282