Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive HIL Testing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908679592214528 |
|---|---|
| author | Feng, Chao Liu, Zihan Gupta, Siddhant Cui, Gongpei von der Assen, Jan Stiller, Burkhard |
| author_facet | Feng, Chao Liu, Zihan Gupta, Siddhant Cui, Gongpei von der Assen, Jan Stiller, Burkhard |
| contents | Hardware-in-the-Loop (HIL) testing is essential for automotive validation but suffers from fragmented and underutilized test artifacts. This paper presents HIL-GPT, a retrieval-augmented generation (RAG) system integrating domain-adapted large language models (LLMs) with semantic retrieval. HIL-GPT leverages embedding fine-tuning using a domain-specific dataset constructed via heuristic mining and LLM-assisted synthesis, combined with vector indexing for scalable, traceable test case and requirement retrieval. Experiments show that fine-tuned compact models, such as \texttt{bge-base-en-v1.5}, achieve a superior trade-off between accuracy, latency, and cost compared to larger models, challenging the notion that bigger is always better. An A/B user study further confirms that RAG-enhanced assistants improve perceived helpfulness, truthfulness, and satisfaction over general-purpose LLMs. These findings provide insights for deploying efficient, domain-aligned LLM-based assistants in industrial HIL environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22584 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive HIL Testing Feng, Chao Liu, Zihan Gupta, Siddhant Cui, Gongpei von der Assen, Jan Stiller, Burkhard Computation and Language Hardware-in-the-Loop (HIL) testing is essential for automotive validation but suffers from fragmented and underutilized test artifacts. This paper presents HIL-GPT, a retrieval-augmented generation (RAG) system integrating domain-adapted large language models (LLMs) with semantic retrieval. HIL-GPT leverages embedding fine-tuning using a domain-specific dataset constructed via heuristic mining and LLM-assisted synthesis, combined with vector indexing for scalable, traceable test case and requirement retrieval. Experiments show that fine-tuned compact models, such as \texttt{bge-base-en-v1.5}, achieve a superior trade-off between accuracy, latency, and cost compared to larger models, challenging the notion that bigger is always better. An A/B user study further confirms that RAG-enhanced assistants improve perceived helpfulness, truthfulness, and satisfaction over general-purpose LLMs. These findings provide insights for deploying efficient, domain-aligned LLM-based assistants in industrial HIL environments. |
| title | Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive HIL Testing |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.22584 |