<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="greco-etal-2025-exploring">
    <titleInfo>
        <title>Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Candida</namePart>
        <namePart type="given">Maria</namePart>
        <namePart type="family">Greco</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lucio</namePart>
        <namePart type="family">La Cava</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lorenzo</namePart>
        <namePart type="family">Zangari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrea</namePart>
        <namePart type="family">Tagarelli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-251-0</identifier>
    </relatedItem>
    <abstract>Morality serves as the foundation of societal structure, guiding legal systems, shaping cultural values, and influencing individual self-perception. With the rise and pervasiveness of generative AI tools, and particularly Large Language Models (LLMs), concerns arise regarding how these tools capture and potentially alter moral dimensions through machine-generated text manipulation. Based on the Moral Foundation Theory, our work investigates this topic by analyzing the behavior of 12 LLMs among the most widely used Open and uncensored (i.e., “abliterated”) models, and leveraging human-annotated datasets used in moral-related analysis. Results have shown varying levels of alteration of moral expressions depending on the type of text modification task and moral-related conditioning prompt.</abstract>
    <identifier type="citekey">greco-etal-2025-exploring</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-long.883</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-long.883/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>18047</start>
            <end>18070</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation
%A Greco, Candida Maria
%A La Cava, Lucio
%A Zangari, Lorenzo
%A Tagarelli, Andrea
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F greco-etal-2025-exploring
%X Morality serves as the foundation of societal structure, guiding legal systems, shaping cultural values, and influencing individual self-perception. With the rise and pervasiveness of generative AI tools, and particularly Large Language Models (LLMs), concerns arise regarding how these tools capture and potentially alter moral dimensions through machine-generated text manipulation. Based on the Moral Foundation Theory, our work investigates this topic by analyzing the behavior of 12 LLMs among the most widely used Open and uncensored (i.e., “abliterated”) models, and leveraging human-annotated datasets used in moral-related analysis. Results have shown varying levels of alteration of moral expressions depending on the type of text modification task and moral-related conditioning prompt.
%R 10.18653/v1/2025.acl-long.883
%U https://aclanthology.org/2025.acl-long.883/
%U https://doi.org/10.18653/v1/2025.acl-long.883
%P 18047-18070

Markdown (Informal)

[Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation](https://aclanthology.org/2025.acl-long.883/) (Greco et al., ACL 2025)

• Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation (Greco et al., ACL 2025)

ACL

• Candida Maria Greco, Lucio La Cava, Lorenzo Zangari, and Andrea Tagarelli. 2025. Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 18047–18070, Vienna, Austria. Association for Computational Linguistics.