SEAINov 20, 2024

Towards Specification-Driven LLM-Based Generation of Embedded Automotive Software

arXiv:2411.13269v113 citationsh-index: 3AISoLA
Originality Incremental advance
AI Analysis

This addresses the challenge of producing critical embedded software for automotive systems, though it appears incremental as it builds on existing LLM and verification methods.

The paper tackles the problem of generating embedded automotive software from specifications using LLMs combined with formal verification, and finds that formally correct code can be generated without iterative backprompting and fine-tuning in industrial case studies.

The paper studies how code generation by LLMs can be combined with formal verification to produce critical embedded software. The first contribution is a general framework, spec2code, in which LLMs are combined with different types of critics that produce feedback for iterative backprompting and fine-tuning. The second contribution presents a first feasibility study, where a minimalistic instantiation of spec2code, without iterative backprompting and fine-tuning, is empirically evaluated using three industrial case studies from the heavy vehicle manufacturer Scania. The goal is to automatically generate industrial-quality code from specifications only. Different combinations of formal ACSL specifications and natural language specifications are explored. The results indicate that formally correct code can be generated even without the application of iterative backprompting and fine-tuning.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes