From Untestable to Testable: Metamorphic Testing in the Age of LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Terragni, Valerio
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910073597460480
author Terragni, Valerio
author_facet Terragni, Valerio
contents This article discusses the challenges of testing software systems with increasingly integrated AI and LLM functionalities. LLMs are powerful but unreliable, and labeled ground truth for testing rarely scales. Metamorphic Testing solves this by turning relations among multiple test executions into executable test oracles.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24774
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Untestable to Testable: Metamorphic Testing in the Age of LLMs
Terragni, Valerio
Software Engineering
Artificial Intelligence
D.2.5; I.2.7
This article discusses the challenges of testing software systems with increasingly integrated AI and LLM functionalities. LLMs are powerful but unreliable, and labeled ground truth for testing rarely scales. Metamorphic Testing solves this by turning relations among multiple test executions into executable test oracles.
title From Untestable to Testable: Metamorphic Testing in the Age of LLMs
topic Software Engineering
Artificial Intelligence
D.2.5; I.2.7
url https://arxiv.org/abs/2603.24774