@inproceedings{hill-2026-concepts,
title = "Concepts at Work: Testing Rival Conceptions of Liberty in Large Language Models",
author = "Hill, Mark J.",
editor = "Xiong, Deyi and
Branco, Ant{\'o}nio and
Zhang, Hongming and
Dong, Yue and
Wang, Benyou and
Zhang, Wenxuan and
Zhou, Li and
Zheng, Jingting",
booktitle = "Proceedings of the First Workshop on Pluralistic Value Alignment of {LLM}s",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.plurvallm-1.6/",
pages = "78--92",
ISBN = "979-8-89176-453-8",
abstract = "Work on pluralistic alignment asks whether language models can represent the range of things people value. That work often treats plurality as disagreement between values, preferences, or cultural positions. We study a different kind of disagreement: two people can share a value and still disagree about its meaning. Liberty is an example. On one view, you are unfree when someone blocks actions. On another, you are unfree when actions depend on unchecked power. We ask whether models prompted to hold one of these conceptual views are able to make it legible, transferable, and operative. We test this with five instruction-tuned models and one frontier reasoning model on 20 vignettes across five domains. Results show prompted views are usually legible and transferable, and these positions can coexist with reduced operativeness. Additionally, when we impose no view at all, models more often default to a non-domination conception of freedom."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hill-2026-concepts">
<titleInfo>
<title>Concepts at Work: Testing Rival Conceptions of Liberty in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Hill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Pluralistic Value Alignment of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Branco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benyou</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingting</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-453-8</identifier>
</relatedItem>
<abstract>Work on pluralistic alignment asks whether language models can represent the range of things people value. That work often treats plurality as disagreement between values, preferences, or cultural positions. We study a different kind of disagreement: two people can share a value and still disagree about its meaning. Liberty is an example. On one view, you are unfree when someone blocks actions. On another, you are unfree when actions depend on unchecked power. We ask whether models prompted to hold one of these conceptual views are able to make it legible, transferable, and operative. We test this with five instruction-tuned models and one frontier reasoning model on 20 vignettes across five domains. Results show prompted views are usually legible and transferable, and these positions can coexist with reduced operativeness. Additionally, when we impose no view at all, models more often default to a non-domination conception of freedom.</abstract>
<identifier type="citekey">hill-2026-concepts</identifier>
<location>
<url>https://aclanthology.org/2026.plurvallm-1.6/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>78</start>
<end>92</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Concepts at Work: Testing Rival Conceptions of Liberty in Large Language Models
%A Hill, Mark J.
%Y Xiong, Deyi
%Y Branco, António
%Y Zhang, Hongming
%Y Dong, Yue
%Y Wang, Benyou
%Y Zhang, Wenxuan
%Y Zhou, Li
%Y Zheng, Jingting
%S Proceedings of the First Workshop on Pluralistic Value Alignment of LLMs
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-453-8
%F hill-2026-concepts
%X Work on pluralistic alignment asks whether language models can represent the range of things people value. That work often treats plurality as disagreement between values, preferences, or cultural positions. We study a different kind of disagreement: two people can share a value and still disagree about its meaning. Liberty is an example. On one view, you are unfree when someone blocks actions. On another, you are unfree when actions depend on unchecked power. We ask whether models prompted to hold one of these conceptual views are able to make it legible, transferable, and operative. We test this with five instruction-tuned models and one frontier reasoning model on 20 vignettes across five domains. Results show prompted views are usually legible and transferable, and these positions can coexist with reduced operativeness. Additionally, when we impose no view at all, models more often default to a non-domination conception of freedom.
%U https://aclanthology.org/2026.plurvallm-1.6/
%P 78-92
Markdown (Informal)
[Concepts at Work: Testing Rival Conceptions of Liberty in Large Language Models](https://aclanthology.org/2026.plurvallm-1.6/) (Hill, PlurVA-LLM 2026)
ACL