@inproceedings{telkamp-hulsebos-2026-towards,
title = "Towards Contextual Sensitive Data Detection",
author = "Telkamp, Liang and
Hulsebos, Madelon",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1939/",
doi = "10.18653/2026.findings-emnlp.1939",
pages = "41354--41364",
ISBN = "979-8-89176-462-0",
abstract = "The emergence of open data portals necessitates more attention to protecting sensitive data before datasets get published and used. To do so effectively, we observe the need to refine and broaden our definitions of sensitive data. We argue that the sensitivity of data depends on its context, and that this context should be considered in methods for assessing data sensitivity. To this end, we introduce a framework, termed ConSenser, for contextual sensitive data detection based on two aspects: 1) type contextualization, which considers the type of data values within the overall context of the dataset or document to assess their true sensitivity, and 2) domain contextualization, which assesses the sensitivity of data values informed by domain-specific information external to the dataset, such as geographic origin of a dataset. Experiments instrumented with language models confirm that type-contextualization significantly reduces the number of false positives for type-based sensitive data detection and reaches a recall of 94{\%} compared to 63{\%} with commonly used tools. Moreover, domain-contextualization through retrieval of sensitivity rules effectively grounds sensitive data detection in relevant context in non-standard data domains. A case study with humanitarian data experts also illustrates that context-grounded explanations provide useful guidance in manual data auditing processes. We open-source the code and annotated datasets at https://github.com/trl-lab/sensitive-data-detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="telkamp-hulsebos-2026-towards">
<titleInfo>
<title>Towards Contextual Sensitive Data Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Telkamp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madelon</namePart>
<namePart type="family">Hulsebos</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>The emergence of open data portals necessitates more attention to protecting sensitive data before datasets get published and used. To do so effectively, we observe the need to refine and broaden our definitions of sensitive data. We argue that the sensitivity of data depends on its context, and that this context should be considered in methods for assessing data sensitivity. To this end, we introduce a framework, termed ConSenser, for contextual sensitive data detection based on two aspects: 1) type contextualization, which considers the type of data values within the overall context of the dataset or document to assess their true sensitivity, and 2) domain contextualization, which assesses the sensitivity of data values informed by domain-specific information external to the dataset, such as geographic origin of a dataset. Experiments instrumented with language models confirm that type-contextualization significantly reduces the number of false positives for type-based sensitive data detection and reaches a recall of 94% compared to 63% with commonly used tools. Moreover, domain-contextualization through retrieval of sensitivity rules effectively grounds sensitive data detection in relevant context in non-standard data domains. A case study with humanitarian data experts also illustrates that context-grounded explanations provide useful guidance in manual data auditing processes. We open-source the code and annotated datasets at https://github.com/trl-lab/sensitive-data-detection.</abstract>
<identifier type="citekey">telkamp-hulsebos-2026-towards</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1939</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1939/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>41354</start>
<end>41364</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Contextual Sensitive Data Detection
%A Telkamp, Liang
%A Hulsebos, Madelon
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F telkamp-hulsebos-2026-towards
%X The emergence of open data portals necessitates more attention to protecting sensitive data before datasets get published and used. To do so effectively, we observe the need to refine and broaden our definitions of sensitive data. We argue that the sensitivity of data depends on its context, and that this context should be considered in methods for assessing data sensitivity. To this end, we introduce a framework, termed ConSenser, for contextual sensitive data detection based on two aspects: 1) type contextualization, which considers the type of data values within the overall context of the dataset or document to assess their true sensitivity, and 2) domain contextualization, which assesses the sensitivity of data values informed by domain-specific information external to the dataset, such as geographic origin of a dataset. Experiments instrumented with language models confirm that type-contextualization significantly reduces the number of false positives for type-based sensitive data detection and reaches a recall of 94% compared to 63% with commonly used tools. Moreover, domain-contextualization through retrieval of sensitivity rules effectively grounds sensitive data detection in relevant context in non-standard data domains. A case study with humanitarian data experts also illustrates that context-grounded explanations provide useful guidance in manual data auditing processes. We open-source the code and annotated datasets at https://github.com/trl-lab/sensitive-data-detection.
%R 10.18653/2026.findings-emnlp.1939
%U https://aclanthology.org/2026.findings-emnlp.1939/
%U https://doi.org/10.18653/2026.findings-emnlp.1939
%P 41354-41364
Markdown (Informal)
[Towards Contextual Sensitive Data Detection](https://aclanthology.org/2026.findings-emnlp.1939/) (Telkamp & Hulsebos, Findings 2026)
ACL
- Liang Telkamp and Madelon Hulsebos. 2026. Towards Contextual Sensitive Data Detection. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 41354–41364, Budapest, Hungary. Association for Computational Linguistics.