@inproceedings{beyranvand-etal-2025-gear,
title = "{GEAR}: A Scalable and Interpretable Evaluation Framework for {RAG}-Based Car Assistant Systems",
author = "Beyranvand, Niloufar and
Dastmalchi, Hamidreza and
An, Aijun and
Davoudi, Heidar and
Chan, Winston and
DiCarlantonio, Ron",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.187/",
pages = "2792--2810",
ISBN = "979-8-89176-333-3",
abstract = "Large language models (LLMs) increasingly power car assistants, enabling natural language interaction for tasks such as maintenance, troubleshooting, and operational guidance. While retrieval-augmented generation (RAG) improves grounding using vehicle manuals, evaluating response quality remains a key challenge. Traditional metrics like BLEU and ROUGE fail to capture critical aspects such as factual accuracy and information coverage. We propose GEAR, a fully automated, reference-based evaluation framework for car assistant systems. GEAR uses LLMs as evaluators to compare assistant responses against ground-truth counterparts, assessing coverage, correctness, and other dimensions of answer quality. To enable fine-grained evaluation, both responses are decomposed into key facts and labeled as essential, optional, or safety-critical using LLMs. The evaluator then determines which of these facts are correct and covered. Experiments show that GEAR aligns closely with human annotations, offering a scalable and reliable solution for evaluating car assistants."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beyranvand-etal-2025-gear">
<titleInfo>
<title>GEAR: A Scalable and Interpretable Evaluation Framework for RAG-Based Car Assistant Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niloufar</namePart>
<namePart type="family">Beyranvand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamidreza</namePart>
<namePart type="family">Dastmalchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aijun</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heidar</namePart>
<namePart type="family">Davoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Winston</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ron</namePart>
<namePart type="family">DiCarlantonio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>Large language models (LLMs) increasingly power car assistants, enabling natural language interaction for tasks such as maintenance, troubleshooting, and operational guidance. While retrieval-augmented generation (RAG) improves grounding using vehicle manuals, evaluating response quality remains a key challenge. Traditional metrics like BLEU and ROUGE fail to capture critical aspects such as factual accuracy and information coverage. We propose GEAR, a fully automated, reference-based evaluation framework for car assistant systems. GEAR uses LLMs as evaluators to compare assistant responses against ground-truth counterparts, assessing coverage, correctness, and other dimensions of answer quality. To enable fine-grained evaluation, both responses are decomposed into key facts and labeled as essential, optional, or safety-critical using LLMs. The evaluator then determines which of these facts are correct and covered. Experiments show that GEAR aligns closely with human annotations, offering a scalable and reliable solution for evaluating car assistants.</abstract>
<identifier type="citekey">beyranvand-etal-2025-gear</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.187/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2792</start>
<end>2810</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GEAR: A Scalable and Interpretable Evaluation Framework for RAG-Based Car Assistant Systems
%A Beyranvand, Niloufar
%A Dastmalchi, Hamidreza
%A An, Aijun
%A Davoudi, Heidar
%A Chan, Winston
%A DiCarlantonio, Ron
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F beyranvand-etal-2025-gear
%X Large language models (LLMs) increasingly power car assistants, enabling natural language interaction for tasks such as maintenance, troubleshooting, and operational guidance. While retrieval-augmented generation (RAG) improves grounding using vehicle manuals, evaluating response quality remains a key challenge. Traditional metrics like BLEU and ROUGE fail to capture critical aspects such as factual accuracy and information coverage. We propose GEAR, a fully automated, reference-based evaluation framework for car assistant systems. GEAR uses LLMs as evaluators to compare assistant responses against ground-truth counterparts, assessing coverage, correctness, and other dimensions of answer quality. To enable fine-grained evaluation, both responses are decomposed into key facts and labeled as essential, optional, or safety-critical using LLMs. The evaluator then determines which of these facts are correct and covered. Experiments show that GEAR aligns closely with human annotations, offering a scalable and reliable solution for evaluating car assistants.
%U https://aclanthology.org/2025.emnlp-industry.187/
%P 2792-2810
Markdown (Informal)
[GEAR: A Scalable and Interpretable Evaluation Framework for RAG-Based Car Assistant Systems](https://aclanthology.org/2025.emnlp-industry.187/) (Beyranvand et al., EMNLP 2025)
ACL