<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="livyatan-etal-2026-moralink">
    <titleInfo>
        <title>MoraLink: Bridging Morals and Narrative Fables for Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lior</namePart>
        <namePart type="family">Livyatan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kai</namePart>
        <namePart type="given">Golan</namePart>
        <namePart type="family">Hashiloni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Asif</namePart>
        <namePart type="family">Amar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roei</namePart>
        <namePart type="family">Rahamim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kfir</namePart>
        <namePart type="family">Bar</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>A fable is a short narrative whose purpose is to convey a moral lesson. While semantically related, morals and fables differ fundamentally in form: morals are abstract and propositional, while fables express the same idea through characters and plot. In this work, we ask how well this conceptual relationship is captured in the latent representations of embedding models. To study this, we introduce MoraLink, a benchmark for moral-to-fable retrieval in which models must retrieve the correct fable for a given moral. We find that off-the-shelf embedding models struggle with this task, and that augmenting fable documents with LLM-generated moral-style summaries substantially improves retrieval, identifying document representation as the primary bottleneck. Contrastive fine-tuning further improves performance, and we release MoraLink as a challenging testbed for probing how well embedding models capture the abstraction gap between a moral principle and the narrative that embodies it.</abstract>
    <identifier type="citekey">livyatan-etal-2026-moralink</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.2106</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2106/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>44855</start>
            <end>44885</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MoraLink: Bridging Morals and Narrative Fables for Retrieval
%A Livyatan, Lior
%A Hashiloni, Kai Golan
%A Amar, Asif
%A Rahamim, Roei
%A Bar, Kfir
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F livyatan-etal-2026-moralink
%X A fable is a short narrative whose purpose is to convey a moral lesson. While semantically related, morals and fables differ fundamentally in form: morals are abstract and propositional, while fables express the same idea through characters and plot. In this work, we ask how well this conceptual relationship is captured in the latent representations of embedding models. To study this, we introduce MoraLink, a benchmark for moral-to-fable retrieval in which models must retrieve the correct fable for a given moral. We find that off-the-shelf embedding models struggle with this task, and that augmenting fable documents with LLM-generated moral-style summaries substantially improves retrieval, identifying document representation as the primary bottleneck. Contrastive fine-tuning further improves performance, and we release MoraLink as a challenging testbed for probing how well embedding models capture the abstraction gap between a moral principle and the narrative that embodies it.
%R 10.18653/2026.findings-emnlp.2106
%U https://aclanthology.org/2026.findings-emnlp.2106/
%U https://doi.org/10.18653/2026.findings-emnlp.2106
%P 44855-44885

Markdown (Informal)

[MoraLink: Bridging Morals and Narrative Fables for Retrieval](https://aclanthology.org/2026.findings-emnlp.2106/) (Livyatan et al., Findings 2026)

• MoraLink: Bridging Morals and Narrative Fables for Retrieval (Livyatan et al., Findings 2026)

ACL

• Lior Livyatan, Kai Golan Hashiloni, Asif Amar, Roei Rahamim, and Kfir Bar. 2026. MoraLink: Bridging Morals and Narrative Fables for Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 44855–44885, Budapest, Hungary. Association for Computational Linguistics.