@inproceedings{liebeskind-etal-2026-representing,
title = "Representing Human Values in Argumentation: A Linguistically Grounded Comparison of Lexicons, Embeddings, and {LLM}s",
author = "Liebeskind, Chaya and
Lewandowska-Tomaszczyk, Barbara and
Liebeskind, Shmuel",
editor = "Sousa-Silva, Rui and
Lopes Cardoso, Henrique and
Koponen, Maarit and
Pareja-Lora, Antonio",
booktitle = "Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era ({LUHME} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.luhme-1.15/",
pages = "183--196",
ISBN = "979-8-89176-471-2",
abstract = "Human values are enduring motivational principles that shape how people argue, justify, and evaluate social issues. While prior work has largely approached value detection as a standard classification problem, we investigate what values look like linguistically and whether computational models reflect aspects of the structure proposed by Schwartz{'}s theory of basic human values. Using the training partition of the Touch{\'e} ValueEval corpus, we compare lexical resources, linguistic markers, supervised classifiers over TF{--}IDF and sentence embeddings, an automated model-search procedure, a zero-shot large language model (Gemini 3.5 Flash), and a transformer embedding baseline (all-MiniLM-L6-v2). On a shared 124-item test split, the three dense semantic approaches form a statistically indistinguishable high-performing tier (macro-F1 0.529{--}0.591) and achieve substantially higher scores than the sparse lexical methods, highlighting the importance of contextual semantic representation in this setting. A constructed diagnostic sanity check shows that deontic modals, universal quantifiers, and abstract nouns behave in the expected direction for value-bearing versus opinion language; however, these cues provide little information for distinguishing individual values in the Touch{\'e} data. Performance is less stable for low-support value categories. Qualitative inspection of model confusions reveals several patterns consistent with theoretically close Schwartz values, alongside confusions between more distant categories; circumplex adjacency is not formally tested. Overall, the results suggest a distinction between surface linguistic cues associated with value-bearing language and the contextual semantic information involved in distinguishing specific values, while offering qualitative evidence that some model confusions align with relationships in Schwartz{'}s motivational structure."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liebeskind-etal-2026-representing">
<titleInfo>
<title>Representing Human Values in Argumentation: A Linguistically Grounded Comparison of Lexicons, Embeddings, and LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaya</namePart>
<namePart type="family">Liebeskind</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Lewandowska-Tomaszczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shmuel</namePart>
<namePart type="family">Liebeskind</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 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Sousa-Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrique</namePart>
<namePart type="family">Lopes Cardoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Pareja-Lora</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">979-8-89176-471-2</identifier>
</relatedItem>
<abstract>Human values are enduring motivational principles that shape how people argue, justify, and evaluate social issues. While prior work has largely approached value detection as a standard classification problem, we investigate what values look like linguistically and whether computational models reflect aspects of the structure proposed by Schwartz’s theory of basic human values. Using the training partition of the Touché ValueEval corpus, we compare lexical resources, linguistic markers, supervised classifiers over TF–IDF and sentence embeddings, an automated model-search procedure, a zero-shot large language model (Gemini 3.5 Flash), and a transformer embedding baseline (all-MiniLM-L6-v2). On a shared 124-item test split, the three dense semantic approaches form a statistically indistinguishable high-performing tier (macro-F1 0.529–0.591) and achieve substantially higher scores than the sparse lexical methods, highlighting the importance of contextual semantic representation in this setting. A constructed diagnostic sanity check shows that deontic modals, universal quantifiers, and abstract nouns behave in the expected direction for value-bearing versus opinion language; however, these cues provide little information for distinguishing individual values in the Touché data. Performance is less stable for low-support value categories. Qualitative inspection of model confusions reveals several patterns consistent with theoretically close Schwartz values, alongside confusions between more distant categories; circumplex adjacency is not formally tested. Overall, the results suggest a distinction between surface linguistic cues associated with value-bearing language and the contextual semantic information involved in distinguishing specific values, while offering qualitative evidence that some model confusions align with relationships in Schwartz’s motivational structure.</abstract>
<identifier type="citekey">liebeskind-etal-2026-representing</identifier>
<location>
<url>https://aclanthology.org/2026.luhme-1.15/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>183</start>
<end>196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Representing Human Values in Argumentation: A Linguistically Grounded Comparison of Lexicons, Embeddings, and LLMs
%A Liebeskind, Chaya
%A Lewandowska-Tomaszczyk, Barbara
%A Liebeskind, Shmuel
%Y Sousa-Silva, Rui
%Y Lopes Cardoso, Henrique
%Y Koponen, Maarit
%Y Pareja-Lora, Antonio
%S Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-471-2
%F liebeskind-etal-2026-representing
%X Human values are enduring motivational principles that shape how people argue, justify, and evaluate social issues. While prior work has largely approached value detection as a standard classification problem, we investigate what values look like linguistically and whether computational models reflect aspects of the structure proposed by Schwartz’s theory of basic human values. Using the training partition of the Touché ValueEval corpus, we compare lexical resources, linguistic markers, supervised classifiers over TF–IDF and sentence embeddings, an automated model-search procedure, a zero-shot large language model (Gemini 3.5 Flash), and a transformer embedding baseline (all-MiniLM-L6-v2). On a shared 124-item test split, the three dense semantic approaches form a statistically indistinguishable high-performing tier (macro-F1 0.529–0.591) and achieve substantially higher scores than the sparse lexical methods, highlighting the importance of contextual semantic representation in this setting. A constructed diagnostic sanity check shows that deontic modals, universal quantifiers, and abstract nouns behave in the expected direction for value-bearing versus opinion language; however, these cues provide little information for distinguishing individual values in the Touché data. Performance is less stable for low-support value categories. Qualitative inspection of model confusions reveals several patterns consistent with theoretically close Schwartz values, alongside confusions between more distant categories; circumplex adjacency is not formally tested. Overall, the results suggest a distinction between surface linguistic cues associated with value-bearing language and the contextual semantic information involved in distinguishing specific values, while offering qualitative evidence that some model confusions align with relationships in Schwartz’s motivational structure.
%U https://aclanthology.org/2026.luhme-1.15/
%P 183-196
Markdown (Informal)
[Representing Human Values in Argumentation: A Linguistically Grounded Comparison of Lexicons, Embeddings, and LLMs](https://aclanthology.org/2026.luhme-1.15/) (Liebeskind et al., LUHME 2026)
ACL