<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2026-smarter">
    <titleInfo>
        <title>Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chao</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zihan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Siddhant</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jan</namePart>
        <namePart type="given">von</namePart>
        <namePart type="given">der</namePart>
        <namePart type="family">Assen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Georg</namePart>
            <namePart type="family">Rehm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mei</namePart>
            <namePart type="family">Tu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-394-4</identifier>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">feng-etal-2026-smarter</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-industry.2/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>5</start>
            <end>12</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing
%A Feng, Chao
%A Liu, Zihan
%A Gupta, Siddhant
%A Assen, Jan von der
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F feng-etal-2026-smarter
%X 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.
%U https://aclanthology.org/2026.acl-industry.2/
%P 5-12

Markdown (Informal)

[Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing](https://aclanthology.org/2026.acl-industry.2/) (Feng et al., ACL 2026)

• Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing (Feng et al., ACL 2026)

ACL

• Chao Feng, Zihan Liu, Siddhant Gupta, and Jan von der Assen. 2026. Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 5–12, San Diego, California, USA. Association for Computational Linguistics.