<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shomee-etal-2026-score">
    <titleInfo>
        <title>SCORE: Specificity, Context Utilization, Robustness, and Relevance for Reference-Free LLM Evaluation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Homaira</namePart>
        <namePart type="given">Huda</namePart>
        <namePart type="family">Shomee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rochana</namePart>
        <namePart type="family">Chaturvedi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yangxinyu</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tanwi</namePart>
        <namePart type="family">Mallick</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) are increasingly used to support question answering and decision-making in high-stakes, domain-specific settings such as natural hazard response and infrastructure planning, where effective answers must convey fine-grained, decision-critical details. However, existing evaluation frameworks for retrieval-augmented generation (RAG) and open-ended question answering primarily rely on surface-level similarity, factual consistency, or semantic relevance, and often fail to assess whether responses provide the specific information required for domain-sensitive decisions. To address this gap, we propose a multi-dimensional, reference-free evaluation framework that assesses LLM outputs along four complementary dimensions: specificity, context utilization, robustness to paraphrasing and semantic perturbations, and answer relevance. We introduce ClimateRiskQA, a curated dataset of 1,412 domain-specific question–answer pairs spanning 40 professional roles and seven natural hazard types, and further evaluate on PubMedQA to examine cross-domain generalization. We also conduct human evaluation to assess inter-annotator agreement and alignment between model outputs and human judgments, which highlights the inherent subjectivity of open-ended, domain-specific evaluation. Our results show that no single metric sufficiently captures answer quality in isolation and demonstrate the need for structured, multi-metric evaluation frameworks when deploying LLMs in high-stakes applications.</abstract>
    <identifier type="citekey">shomee-etal-2026-score</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.934/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>21515</start>
            <end>21542</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SCORE: Specificity, Context Utilization, Robustness, and Relevance for Reference-Free LLM Evaluation
%A Shomee, Homaira Huda
%A Chaturvedi, Rochana
%A Xie, Yangxinyu
%A Mallick, Tanwi
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F shomee-etal-2026-score
%X Large language models (LLMs) are increasingly used to support question answering and decision-making in high-stakes, domain-specific settings such as natural hazard response and infrastructure planning, where effective answers must convey fine-grained, decision-critical details. However, existing evaluation frameworks for retrieval-augmented generation (RAG) and open-ended question answering primarily rely on surface-level similarity, factual consistency, or semantic relevance, and often fail to assess whether responses provide the specific information required for domain-sensitive decisions. To address this gap, we propose a multi-dimensional, reference-free evaluation framework that assesses LLM outputs along four complementary dimensions: specificity, context utilization, robustness to paraphrasing and semantic perturbations, and answer relevance. We introduce ClimateRiskQA, a curated dataset of 1,412 domain-specific question–answer pairs spanning 40 professional roles and seven natural hazard types, and further evaluate on PubMedQA to examine cross-domain generalization. We also conduct human evaluation to assess inter-annotator agreement and alignment between model outputs and human judgments, which highlights the inherent subjectivity of open-ended, domain-specific evaluation. Our results show that no single metric sufficiently captures answer quality in isolation and demonstrate the need for structured, multi-metric evaluation frameworks when deploying LLMs in high-stakes applications.
%U https://aclanthology.org/2026.emnlp-main.934/
%P 21515-21542

Markdown (Informal)

[SCORE: Specificity, Context Utilization, Robustness, and Relevance for Reference-Free LLM Evaluation](https://aclanthology.org/2026.emnlp-main.934/) (Shomee et al., EMNLP 2026)

• SCORE: Specificity, Context Utilization, Robustness, and Relevance for Reference-Free LLM Evaluation (Shomee et al., EMNLP 2026)

ACL

• Homaira Huda Shomee, Rochana Chaturvedi, Yangxinyu Xie, and Tanwi Mallick. 2026. SCORE: Specificity, Context Utilization, Robustness, and Relevance for Reference-Free LLM Evaluation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 21515–21542, Budapest, Hungary. Association for Computational Linguistics.