Saved in:
Bibliographic Details
Main Authors: Le, Viet-Man, Tran, Thi Ngoc Trang, Lubos, Sebastian, Felfernig, Alexander, Garber, Damian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.20523
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913054907695104
author Le, Viet-Man
Tran, Thi Ngoc Trang
Lubos, Sebastian
Felfernig, Alexander
Garber, Damian
author_facet Le, Viet-Man
Tran, Thi Ngoc Trang
Lubos, Sebastian
Felfernig, Alexander
Garber, Damian
contents We study whether Large Language Models (LLMs) can perform feature model analysis operations (AOs) directly on semi-formal textual blueprints, i.e., concise constrained-language descriptions of feature hierarchies and constraints, enabling early validation in Software Product Line scoping. Using 12 state-of-the-art LLMs and 16 standard AOs, we compare their outputs against the solver-based oracle FLAMA. Results show that reasoning-optimized models (e.g., Grok 4 Fast Reasoning, Gemini 2.5 Pro) achieve 88-89% average accuracy across all evaluated blueprints and operations, approaching solver correctness. We identify systematic errors in structural parsing and constraint reasoning, and highlight accuracy-cost trade-offs that inform model selection. These findings position LLMs as lightweight assistants for early variability validation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20523
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis
Le, Viet-Man
Tran, Thi Ngoc Trang
Lubos, Sebastian
Felfernig, Alexander
Garber, Damian
Software Engineering
Artificial Intelligence
We study whether Large Language Models (LLMs) can perform feature model analysis operations (AOs) directly on semi-formal textual blueprints, i.e., concise constrained-language descriptions of feature hierarchies and constraints, enabling early validation in Software Product Line scoping. Using 12 state-of-the-art LLMs and 16 standard AOs, we compare their outputs against the solver-based oracle FLAMA. Results show that reasoning-optimized models (e.g., Grok 4 Fast Reasoning, Gemini 2.5 Pro) achieve 88-89% average accuracy across all evaluated blueprints and operations, approaching solver correctness. We identify systematic errors in structural parsing and constraint reasoning, and highlight accuracy-cost trade-offs that inform model selection. These findings position LLMs as lightweight assistants for early variability validation.
title Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2604.20523