*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation

Quentin Lemesle; Léane Jourdan; Daisy Munson; Pierre Alain; Jonathan Chevelu; Arnaud Delhay; Damien Lolive

*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation

Quentin Lemesle, Leane Jourdan, Daisy Munson, Pierre Alain, Jonathan Chevelu, Arnaud Delhay, Damien Lolive

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

Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive and require post-processing. To address these limitations, we build upon ParaPLUIE, a perplexity-based LLM-judge metric that estimates confidence over “Yes/No” answers without generating text. We introduce *-PLUIE, task-specific prompting variants of ParaPLUIE and evaluate their alignment with human judgement. Our experiments show that personalised *-PLUIE achieves stronger correlations with human ratings while maintaining low computational cost.

Anthology ID:: 2026.starsem-conference.14
Volume:: Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)
Month:: July
Year:: 2026
Address:: San Diego, California, United States
Editors:: Saif M. Mohammad, Nedjma Ousidhoum
Venues:: *SEM | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 211–243
Language:
URL:: https://aclanthology.org/2026.starsem-conference.14/
DOI:
Bibkey:
Cite (ACL):: Quentin Lemesle, Leane Jourdan, Daisy Munson, Pierre Alain, Jonathan Chevelu, Arnaud Delhay, and Damien Lolive. 2026. *-PLUIE: Personalisable metric with Llm Used for Improved Evaluation. In Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026), pages 211–243, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):: *-PLUIE: Personalisable metric with Llm Used for Improved Evaluation (Lemesle et al., *SEM 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.starsem-conference.14.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{lemesle-etal-2026-pluie,
    title = "*-{PLUIE}: Personalisable metric with Llm Used for Improved Evaluation",
    author = "Lemesle, Quentin  and
      Jourdan, Leane  and
      Munson, Daisy  and
      Alain, Pierre  and
      Chevelu, Jonathan  and
      Delhay, Arnaud  and
      Lolive, Damien",
    editor = "Mohammad, Saif M.  and
      Ousidhoum, Nedjma",
    booktitle = "Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*{SEM} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.starsem-conference.14/",
    pages = "211--243",
    ISBN = "979-8-89176-413-2",
    abstract = "Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive and require post-processing. To address these limitations, we build upon ParaPLUIE, a perplexity-based LLM-judge metric that estimates confidence over ``Yes/No'' answers without generating text. We introduce *-PLUIE, task-specific prompting variants of ParaPLUIE and evaluate their alignment with human judgement. Our experiments show that personalised *-PLUIE achieves stronger correlations with human ratings while maintaining low computational cost."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lemesle-etal-2026-pluie">
    <titleInfo>
        <title>*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Quentin</namePart>
        <namePart type="family">Lemesle</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Leane</namePart>
        <namePart type="family">Jourdan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daisy</namePart>
        <namePart type="family">Munson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pierre</namePart>
        <namePart type="family">Alain</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Chevelu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arnaud</namePart>
        <namePart type="family">Delhay</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Damien</namePart>
        <namePart type="family">Lolive</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 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saif</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Mohammad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nedjma</namePart>
            <namePart type="family">Ousidhoum</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, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-413-2</identifier>
    </relatedItem>
    <abstract>Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive and require post-processing. To address these limitations, we build upon ParaPLUIE, a perplexity-based LLM-judge metric that estimates confidence over “Yes/No” answers without generating text. We introduce *-PLUIE, task-specific prompting variants of ParaPLUIE and evaluate their alignment with human judgement. Our experiments show that personalised *-PLUIE achieves stronger correlations with human ratings while maintaining low computational cost.</abstract>
    <identifier type="citekey">lemesle-etal-2026-pluie</identifier>
    <location>
        <url>https://aclanthology.org/2026.starsem-conference.14/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>211</start>
            <end>243</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T *-PLUIE: Personalisable metric with Llm Used for Improved Evaluation
%A Lemesle, Quentin
%A Jourdan, Leane
%A Munson, Daisy
%A Alain, Pierre
%A Chevelu, Jonathan
%A Delhay, Arnaud
%A Lolive, Damien
%Y Mohammad, Saif M.
%Y Ousidhoum, Nedjma
%S Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-413-2
%F lemesle-etal-2026-pluie
%X Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive and require post-processing. To address these limitations, we build upon ParaPLUIE, a perplexity-based LLM-judge metric that estimates confidence over “Yes/No” answers without generating text. We introduce *-PLUIE, task-specific prompting variants of ParaPLUIE and evaluate their alignment with human judgement. Our experiments show that personalised *-PLUIE achieves stronger correlations with human ratings while maintaining low computational cost.
%U https://aclanthology.org/2026.starsem-conference.14/
%P 211-243

Download as File

Markdown (Informal)

[*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation](https://aclanthology.org/2026.starsem-conference.14/) (Lemesle et al., *SEM 2026)

*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation (Lemesle et al., *SEM 2026)

ACL

Quentin Lemesle, Leane Jourdan, Daisy Munson, Pierre Alain, Jonathan Chevelu, Arnaud Delhay, and Damien Lolive. 2026. *-PLUIE: Personalisable metric with Llm Used for Improved Evaluation. In Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026), pages 211–243, San Diego, California, United States. Association for Computational Linguistics.