Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems

Arif Türkmen; Kaan Efe Keleş

Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

We study retrieval-augmented generation (RAG) evaluation in the Trendyol QA Assistant using 150k real e-commerce interactions. Our framework combines user satisfaction labels, LLM-as-a-judge scoring, and factor-based diagnostics to separate retrieval from generation errors. We find that judge models broadly reflect user satisfaction trends, though important nuances of dissatisfaction are often missed. Factor-level analysis highlights systematic error patterns across query types and context quality, demonstrating that hybrid evaluation, combining multiple LLM judges with direct user feedback offers the most reliable assessment strategy for production RAG systems.

Anthology ID:: 2026.mme-main.12
Volume:: Proceedings of the First Workshop on Multilingual Multicultural Evaluation
Month:: March
Year:: 2026
Address:: Rabat, Morocco
Editors:: Pinzhen Chen, Vilém Zouhar, Hanxu Hu, Simran Khanuja, Wenhao Zhu, Barry Haddow, Alexandra Birch, Alham Fikri Aji, Rico Sennrich, Sara Hooker
Venues:: MME | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 189–195
Language:
URL:: https://aclanthology.org/2026.mme-main.12/
DOI:
Bibkey:
Cite (ACL):: Arif Türkmen and Kaan Efe Keleş. 2026. Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems. In Proceedings of the First Workshop on Multilingual Multicultural Evaluation, pages 189–195, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):: Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems (Türkmen & Keleş, MME 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.mme-main.12.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{turkmen-keles-2026-trust,
    title = "Whom to Trust? Analyzing the Divergence Between User Satisfaction and {LLM}-as-a-Judge in {E}-Commerce {RAG} Systems",
    author = {T{\"u}rkmen, Arif  and
      Kele{\c{s}}, Kaan Efe},
    editor = "Chen, Pinzhen  and
      Zouhar, Vil{\'e}m  and
      Hu, Hanxu  and
      Khanuja, Simran  and
      Zhu, Wenhao  and
      Haddow, Barry  and
      Birch, Alexandra  and
      Aji, Alham Fikri  and
      Sennrich, Rico  and
      Hooker, Sara",
    booktitle = "Proceedings of the First Workshop on Multilingual Multicultural Evaluation",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.mme-main.12/",
    pages = "189--195",
    ISBN = "979-8-89176-368-5",
    abstract = "We study retrieval-augmented generation (RAG) evaluation in the Trendyol QA Assistant using 150k real e-commerce interactions. Our framework combines user satisfaction labels, LLM-as-a-judge scoring, and factor-based diagnostics to separate retrieval from generation errors. We find that judge models broadly reflect user satisfaction trends, though important nuances of dissatisfaction are often missed. Factor-level analysis highlights systematic error patterns across query types and context quality, demonstrating that hybrid evaluation, combining multiple LLM judges with direct user feedback offers the most reliable assessment strategy for production RAG systems."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="turkmen-keles-2026-trust">
    <titleInfo>
        <title>Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Arif</namePart>
        <namePart type="family">Türkmen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kaan</namePart>
        <namePart type="given">Efe</namePart>
        <namePart type="family">Keleş</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Multilingual Multicultural Evaluation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pinzhen</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vilém</namePart>
            <namePart type="family">Zouhar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hanxu</namePart>
            <namePart type="family">Hu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simran</namePart>
            <namePart type="family">Khanuja</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Wenhao</namePart>
            <namePart type="family">Zhu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Barry</namePart>
            <namePart type="family">Haddow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alexandra</namePart>
            <namePart type="family">Birch</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alham</namePart>
            <namePart type="given">Fikri</namePart>
            <namePart type="family">Aji</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rico</namePart>
            <namePart type="family">Sennrich</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Hooker</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-368-5</identifier>
    </relatedItem>
    <abstract>We study retrieval-augmented generation (RAG) evaluation in the Trendyol QA Assistant using 150k real e-commerce interactions. Our framework combines user satisfaction labels, LLM-as-a-judge scoring, and factor-based diagnostics to separate retrieval from generation errors. We find that judge models broadly reflect user satisfaction trends, though important nuances of dissatisfaction are often missed. Factor-level analysis highlights systematic error patterns across query types and context quality, demonstrating that hybrid evaluation, combining multiple LLM judges with direct user feedback offers the most reliable assessment strategy for production RAG systems.</abstract>
    <identifier type="citekey">turkmen-keles-2026-trust</identifier>
    <location>
        <url>https://aclanthology.org/2026.mme-main.12/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>189</start>
            <end>195</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems
%A Türkmen, Arif
%A Keleş, Kaan Efe
%Y Chen, Pinzhen
%Y Zouhar, Vilém
%Y Hu, Hanxu
%Y Khanuja, Simran
%Y Zhu, Wenhao
%Y Haddow, Barry
%Y Birch, Alexandra
%Y Aji, Alham Fikri
%Y Sennrich, Rico
%Y Hooker, Sara
%S Proceedings of the First Workshop on Multilingual Multicultural Evaluation
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-368-5
%F turkmen-keles-2026-trust
%X We study retrieval-augmented generation (RAG) evaluation in the Trendyol QA Assistant using 150k real e-commerce interactions. Our framework combines user satisfaction labels, LLM-as-a-judge scoring, and factor-based diagnostics to separate retrieval from generation errors. We find that judge models broadly reflect user satisfaction trends, though important nuances of dissatisfaction are often missed. Factor-level analysis highlights systematic error patterns across query types and context quality, demonstrating that hybrid evaluation, combining multiple LLM judges with direct user feedback offers the most reliable assessment strategy for production RAG systems.
%U https://aclanthology.org/2026.mme-main.12/
%P 189-195

Download as File

Markdown (Informal)

[Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems](https://aclanthology.org/2026.mme-main.12/) (Türkmen & Keleş, MME 2026)

Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems (Türkmen & Keleş, MME 2026)

ACL

Arif Türkmen and Kaan Efe Keleş. 2026. Whom to Trust? Analyzing the Divergence Between User Satisfaction and LLM-as-a-Judge in E-Commerce RAG Systems. In Proceedings of the First Workshop on Multilingual Multicultural Evaluation, pages 189–195, Rabat, Morocco. Association for Computational Linguistics.