Towards LLM-Enhanced Product Line Scoping

TL;DR

This paper explores how Large Language Models can assist in product line scoping by enabling natural language interactions to evaluate feature model alternatives, aiming to improve efficiency and decision-making.

Contribution

It proposes a novel approach to integrate LLMs into product line scoping, demonstrating potential benefits over traditional manual analysis methods.

Findings

LLMs can evaluate feature model alternatives effectively.

Natural language interaction simplifies the scoping process.

Open challenges remain in integrating LLMs with existing workflows.

Abstract

The idea of product line scoping is to identify the set of features and configurations that a product line should include, i.e., offer for configuration purposes. In this context, a major scoping task is to find a balance between commercial relevance and technical feasibility. Traditional product line scoping approaches rely on formal feature models and require a manual analysis which can be quite time-consuming. In this paper, we sketch how Large Language Models (LLMs) can be applied to support product line scoping tasks with a natural language interaction based scoping process. Using a working example from the smarthome domain, we sketch how LLMs can be applied to evaluate different feature model alternatives. We discuss open research challenges regarding the integration of LLMs with product line scoping.