Software Defined Vehicle Code Generation: A Few-Shot Prompting Approach

TL;DR

This paper explores using advanced prompt engineering with large language models to generate software code for Software-Defined Vehicles, demonstrating that few-shot prompting significantly improves performance without retraining the models.

Contribution

It introduces a prompt-based approach for SDV code generation, showing that few-shot prompting enhances LLM performance without needing access to proprietary model architectures.

Findings

Few-shot prompting outperforms other techniques in SDV code generation

A benchmark was created to evaluate LLMs in this domain

Prompt engineering can effectively adapt LLMs for specific tasks

Abstract

The emergence of Software-Defined Vehicles (SDVs) marks a paradigm shift in the automotive industry, where software now plays a pivotal role in defining vehicle functionality, enabling rapid innovation of modern vehicles. Developing SDV-specific applications demands advanced tools to streamline code generation and improve development efficiency. In recent years, general-purpose large language models (LLMs) have demonstrated transformative potential across domains. Still, restricted access to proprietary model architectures hinders their adaption to specific tasks like SDV code generation. In this study, we propose using prompts, a common and basic strategy to interact with LLMs and redirect their responses. Using only system prompts with an appropriate and efficient prompt structure designed using advanced prompt engineering techniques, LLMs can be crafted without requiring a training session or access to their base design. This research investigates the extensive experiments on different models by applying various prompting techniques, including bare models, using a benchmark specifically created to evaluate LLMs' performance in generating SDV code. The results reveal that the model with a few-shot prompting strategy outperforms the others in adjusting the LLM answers to match the expected outcomes based on quantitative metrics.