<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kiehne-etal-2022-contextualizing">
    <titleInfo>
        <title>Contextualizing Language Models for Norms Diverging from Social Majority</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Niklas</namePart>
        <namePart type="family">Kiehne</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hermann</namePart>
        <namePart type="family">Kroll</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wolf-Tilo</namePart>
        <namePart type="family">Balke</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>To comprehensibly contextualize decisions, artificial systems in social situations need a high degree of awareness of the rules of conduct of human behavior. Especially transformer-based language models have recently been shown to exhibit some such awareness. But what if norms in some social setting do not adhere to or even blatantly deviate from the mainstream? In this paper, we introduce a novel mechanism based on deontic logic to allow for a flexible adaptation of individual norms by de-biasing training data sets and a task-reduction to textual entailment. Building on the popular ‘Moral Stories’ dataset we on the one hand highlight the intrinsic bias of current language models, on the other hand characterize the adaptability of pre-trained models to deviating norms in fine-tuning settings.</abstract>
    <identifier type="citekey">kiehne-etal-2022-contextualizing</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.339</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.339</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>4620</start>
            <end>4633</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Contextualizing Language Models for Norms Diverging from Social Majority
%A Kiehne, Niklas
%A Kroll, Hermann
%A Balke, Wolf-Tilo
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F kiehne-etal-2022-contextualizing
%X To comprehensibly contextualize decisions, artificial systems in social situations need a high degree of awareness of the rules of conduct of human behavior. Especially transformer-based language models have recently been shown to exhibit some such awareness. But what if norms in some social setting do not adhere to or even blatantly deviate from the mainstream? In this paper, we introduce a novel mechanism based on deontic logic to allow for a flexible adaptation of individual norms by de-biasing training data sets and a task-reduction to textual entailment. Building on the popular ‘Moral Stories’ dataset we on the one hand highlight the intrinsic bias of current language models, on the other hand characterize the adaptability of pre-trained models to deviating norms in fine-tuning settings.
%R 10.18653/v1/2022.findings-emnlp.339
%U https://aclanthology.org/2022.findings-emnlp.339
%U https://doi.org/10.18653/v1/2022.findings-emnlp.339
%P 4620-4633

Markdown (Informal)

[Contextualizing Language Models for Norms Diverging from Social Majority](https://aclanthology.org/2022.findings-emnlp.339) (Kiehne et al., Findings 2022)

• Contextualizing Language Models for Norms Diverging from Social Majority (Kiehne et al., Findings 2022)

ACL

• Niklas Kiehne, Hermann Kroll, and Wolf-Tilo Balke. 2022. Contextualizing Language Models for Norms Diverging from Social Majority. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4620–4633, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.