@inproceedings{dong-etal-2026-contextual,
title = "A Contextual Measure of Ambiguity in Prescriptive Texts",
author = "Dong, Sally and
Thorburn, Luke and
Konya, Andrew and
Bakker, Michiel A.",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2483/",
pages = "56379--56412",
ISBN = "979-8-89176-459-0",
abstract = "Ambiguity or vagueness is a consequential consideration when drafting prescriptive text such as laws, contracts, or organizational policies. As a greater volume of such text is produced by language models, there is a need for valid, scalable methods for quantifying ambiguity, but existing measures are based on lexical properties of text rather than how it is interpreted in context. In this paper, we propose quantifying ambiguity as the degree of disagreement among a set of stakeholders ({''}raters'') on how alternative prescriptive statements ({''}policies'') apply in each of a set of relevant scenarios ({''}cases''). Using two policy domains, we present preliminary analysis suggesting that, even when using simulated raters, this approach (i) correlates with real human disagreement, and (ii) is robust to spurious text features. We then apply the measure to existing deliberation datasets to describe the association between policy ambiguity and support for those policies. A Python package for our framework and all data used in the paper are released at https://github.com/sally-dong/DELTA-ambiguity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2026-contextual">
<titleInfo>
<title>A Contextual Measure of Ambiguity in Prescriptive Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sally</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Thorburn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Konya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michiel</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Bakker</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Ambiguity or vagueness is a consequential consideration when drafting prescriptive text such as laws, contracts, or organizational policies. As a greater volume of such text is produced by language models, there is a need for valid, scalable methods for quantifying ambiguity, but existing measures are based on lexical properties of text rather than how it is interpreted in context. In this paper, we propose quantifying ambiguity as the degree of disagreement among a set of stakeholders (”raters”) on how alternative prescriptive statements (”policies”) apply in each of a set of relevant scenarios (”cases”). Using two policy domains, we present preliminary analysis suggesting that, even when using simulated raters, this approach (i) correlates with real human disagreement, and (ii) is robust to spurious text features. We then apply the measure to existing deliberation datasets to describe the association between policy ambiguity and support for those policies. A Python package for our framework and all data used in the paper are released at https://github.com/sally-dong/DELTA-ambiguity.</abstract>
<identifier type="citekey">dong-etal-2026-contextual</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2483/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>56379</start>
<end>56412</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Contextual Measure of Ambiguity in Prescriptive Texts
%A Dong, Sally
%A Thorburn, Luke
%A Konya, Andrew
%A Bakker, Michiel A.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F dong-etal-2026-contextual
%X Ambiguity or vagueness is a consequential consideration when drafting prescriptive text such as laws, contracts, or organizational policies. As a greater volume of such text is produced by language models, there is a need for valid, scalable methods for quantifying ambiguity, but existing measures are based on lexical properties of text rather than how it is interpreted in context. In this paper, we propose quantifying ambiguity as the degree of disagreement among a set of stakeholders (”raters”) on how alternative prescriptive statements (”policies”) apply in each of a set of relevant scenarios (”cases”). Using two policy domains, we present preliminary analysis suggesting that, even when using simulated raters, this approach (i) correlates with real human disagreement, and (ii) is robust to spurious text features. We then apply the measure to existing deliberation datasets to describe the association between policy ambiguity and support for those policies. A Python package for our framework and all data used in the paper are released at https://github.com/sally-dong/DELTA-ambiguity.
%U https://aclanthology.org/2026.emnlp-main.2483/
%P 56379-56412
Markdown (Informal)
[A Contextual Measure of Ambiguity in Prescriptive Texts](https://aclanthology.org/2026.emnlp-main.2483/) (Dong et al., EMNLP 2026)
ACL
- Sally Dong, Luke Thorburn, Andrew Konya, and Michiel A. Bakker. 2026. A Contextual Measure of Ambiguity in Prescriptive Texts. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 56379–56412, Budapest, Hungary. Association for Computational Linguistics.