@inproceedings{feng-etal-2026-smarter,
    title = "Smarter, not Bigger: Fine-Tuned {RAG}-Enhanced {LLM}s for Automotive Hardware-in-the-Loop Testing",
    author = "Feng, Chao  and
      Liu, Zihan  and
      Gupta, Siddhant  and
      Assen, Jan von der",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.2/",
    pages = "5--12",
    ISBN = "979-8-89176-394-4",
    abstract = "Hardware-in-the-Loop (HIL) testing is essential for automotive validation but suffers from fragmented and underutilized test artifacts. This paper presents HIL-GPT, an industry-deployed retrieval-augmented generation (RAG) system that integrates semantic retrieval with domain-adapted large language models to support test engineers in real-world HIL workflows. The system combines domain-specific embeddings to enable traceable retrieval of test cases and requirements under industrial latency and cost constraints. Through empirical evaluation, we show that compact, domain-adapted models can achieve a favorable trade-off among accuracy, latency, and cost compared to larger general-purpose models, challenging the assumption that larger models are always preferable in industrial NLP systems. An A/B user study further confirms that HIL-GPT improves perceived helpfulness, truthfulness, and satisfaction over general-purpose LLMs."
}