Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis

TL;DR

This study evaluates the effectiveness of large language models in analyzing semi-formal feature blueprints for early validation in software product line engineering, showing promising accuracy levels.

Contribution

It demonstrates that reasoning-optimized LLMs can perform feature model analysis operations with high accuracy, approaching solver-based methods, for early product line validation.

Findings

Grok 4 Fast Reasoning and Gemini 2.5 Pro achieve 88-89% accuracy.

Systematic errors are identified in structural parsing and constraint reasoning.

Trade-offs between accuracy and computational cost are highlighted for model selection.

Abstract

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.