Search papers, labs, and topics across Lattice.
This paper advocates for the incorporation of vibe modeling as an essential intermediate representation in AI-driven software development, addressing the shortcomings of current practices that overly emphasize direct code generation. Through a student survey study, the authors assess perceptions regarding LLM outputs, focusing on understanding, validation effort, trust, and the utility of vibe modeling in various development contexts. The findings indicate that vibe modeling can enhance the interpretability and trustworthiness of AI-generated software artifacts, paving the way for more reliable AI-assisted development processes.
Vibe modeling could be the key to bridging the gap between natural language prompts and trustworthy software generation, enhancing both understanding and validation.
Large Language Models (LLMs) are increasingly used to generate software artifacts from natural language prompts. While this enables rapid prototyping and lowers the barrier to software creation, it also introduces challenges related to understanding, validation, traceability, and trust. In this paper, we argue that current AI-based development practices focus too heavily on the direct generation of code and insufficiently on intermediate representations that preserve human intent and support reasoning about system behavior. We argue for vibe modeling as a lightweight intermediate abstraction between natural language interaction and code generation. To explore its potential, we present a student survey study that examines perceptions of LLM output understanding, validation effort, trust and the perceived usefulness of vibe modeling across several AI-assisted development scenarios. Our results are intended to inform future studies for trustworthy and explainable AI-based software engineering via vibe modeling.
