<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siro-etal-2026-learning">
    <titleInfo>
        <title>Learning to Judge: LLMs Designing and Applying Evaluation Rubrics</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Clemencia</namePart>
        <namePart type="family">Siro</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pourya</namePart>
        <namePart type="family">Aliannejadi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="family">Aliannejadi</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>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</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">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) are increasingly used as evaluators for natural language generation, applying human-defined rubrics to assess system outputs. However, human rubrics are often static and misaligned with how models internally represent language quality. We introduce GER-Eval (Generating Evaluation Rubrics for Evaluation) to investigate whether LLMs can design and use their own evaluation rubrics. We evaluate the semantic coherence and scoring reliability of LLM-defined criteria and their alignment with human criteria. LLMs reliably generate interpretable and task-aware evaluation dimensions and apply them within models, but their scoring reliability degrades in factual and knowledge-intensive settings. Closed-source models such as GPT-4o achieve higher agreement and cross-model generalization than open-weight models such as Llama. Our findings position evaluation as a learned linguistic capability of LLMs—consistent within models but fragmented across them—and call for new methods that jointly model human and LLM evaluative language to improve reliability and interpretability.</abstract>
    <identifier type="citekey">siro-etal-2026-learning</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.335/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>6371</start>
            <end>6389</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to Judge: LLMs Designing and Applying Evaluation Rubrics
%A Siro, Clemencia
%A Aliannejadi, Pourya
%A Aliannejadi, Mohammad
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F siro-etal-2026-learning
%X Large language models (LLMs) are increasingly used as evaluators for natural language generation, applying human-defined rubrics to assess system outputs. However, human rubrics are often static and misaligned with how models internally represent language quality. We introduce GER-Eval (Generating Evaluation Rubrics for Evaluation) to investigate whether LLMs can design and use their own evaluation rubrics. We evaluate the semantic coherence and scoring reliability of LLM-defined criteria and their alignment with human criteria. LLMs reliably generate interpretable and task-aware evaluation dimensions and apply them within models, but their scoring reliability degrades in factual and knowledge-intensive settings. Closed-source models such as GPT-4o achieve higher agreement and cross-model generalization than open-weight models such as Llama. Our findings position evaluation as a learned linguistic capability of LLMs—consistent within models but fragmented across them—and call for new methods that jointly model human and LLM evaluative language to improve reliability and interpretability.
%U https://aclanthology.org/2026.findings-eacl.335/
%P 6371-6389

Markdown (Informal)

[Learning to Judge: LLMs Designing and Applying Evaluation Rubrics](https://aclanthology.org/2026.findings-eacl.335/) (Siro et al., Findings 2026)

• Learning to Judge: LLMs Designing and Applying Evaluation Rubrics (Siro et al., Findings 2026)

ACL

• Clemencia Siro, Pourya Aliannejadi, and Mohammad Aliannejadi. 2026. Learning to Judge: LLMs Designing and Applying Evaluation Rubrics. In Findings of the Association for Computational Linguistics: EACL 2026, pages 6371–6389, Rabat, Morocco. Association for Computational Linguistics.