Generative transformations and patterns in LLM-native approaches for software verification and falsification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Braberman, Víctor A., Bonomo-Braberman, Flavia, Charalambous, Yiannis, Colonna, Juan G., Cordeiro, Lucas C., de Freitas, Rosiane
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914078097670144
author Braberman, Víctor A.
Bonomo-Braberman, Flavia
Charalambous, Yiannis
Colonna, Juan G.
Cordeiro, Lucas C.
de Freitas, Rosiane
author_facet Braberman, Víctor A.
Bonomo-Braberman, Flavia
Charalambous, Yiannis
Colonna, Juan G.
Cordeiro, Lucas C.
de Freitas, Rosiane
contents The emergence of prompting as the dominant paradigm for leveraging Large Language Models (LLMs) has led to a proliferation of LLM-native software, where application behavior arises from complex, stochastic data transformations. However, the engineering of such systems remains largely exploratory and ad-hoc, hampered by the absence of conceptual frameworks, ex-ante methodologies, design guidelines, and specialized benchmarks. We argue that a foundational step towards a more disciplined engineering practice is a systematic understanding of the core functional units--generative transformations--and their compositional patterns within LLM-native applications. Focusing on the rich domain of software verification and falsification, we conduct a secondary study of over 100 research proposals to address this gap. We first present a fine-grained taxonomy of generative transformations, abstracting prompt-based interactions into conceptual signatures. This taxonomy serves as a scaffolding to identify recurrent transformation relationship patterns--analogous to software design patterns--that characterize solution approaches in the literature. Our analysis not only validates the utility of the taxonomy but also surfaces strategic gaps and cross-dimensional relationships, offering a structured foundation for future research in modular and compositional LLM application design, benchmarking, and the development of reliable LLM-native systems.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09384
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative transformations and patterns in LLM-native approaches for software verification and falsification
Braberman, Víctor A.
Bonomo-Braberman, Flavia
Charalambous, Yiannis
Colonna, Juan G.
Cordeiro, Lucas C.
de Freitas, Rosiane
Software Engineering
Artificial Intelligence
Computation and Language
Machine Learning
F.3.1; D.2.4; D.2.5; I.2.7
The emergence of prompting as the dominant paradigm for leveraging Large Language Models (LLMs) has led to a proliferation of LLM-native software, where application behavior arises from complex, stochastic data transformations. However, the engineering of such systems remains largely exploratory and ad-hoc, hampered by the absence of conceptual frameworks, ex-ante methodologies, design guidelines, and specialized benchmarks. We argue that a foundational step towards a more disciplined engineering practice is a systematic understanding of the core functional units--generative transformations--and their compositional patterns within LLM-native applications. Focusing on the rich domain of software verification and falsification, we conduct a secondary study of over 100 research proposals to address this gap. We first present a fine-grained taxonomy of generative transformations, abstracting prompt-based interactions into conceptual signatures. This taxonomy serves as a scaffolding to identify recurrent transformation relationship patterns--analogous to software design patterns--that characterize solution approaches in the literature. Our analysis not only validates the utility of the taxonomy but also surfaces strategic gaps and cross-dimensional relationships, offering a structured foundation for future research in modular and compositional LLM application design, benchmarking, and the development of reliable LLM-native systems.
title Generative transformations and patterns in LLM-native approaches for software verification and falsification
topic Software Engineering
Artificial Intelligence
Computation and Language
Machine Learning
F.3.1; D.2.4; D.2.5; I.2.7
url https://arxiv.org/abs/2404.09384