@inproceedings{gold-etal-2026-veil,
title = "{VEIL}: A Benchmark for Value-Preserving Entity Identification Limitation",
author = "Gold, Darina and
Rastegar, Shadi and
Liebel, Alina and
Zarcone, Alessandra",
editor = {Siegert, Ingo and
Szawerna, Maria Irena and
Choukri, Khalid and
Dobnik, Simon and
Kamocki, Pawe{\l} and
Lindstr{\"o}m Tiedemann, Therese and
Lison, Pierre and
Mu{\~n}oz S{\'a}nchez, Ricardo and
Pil{\'a}n, Ildik{\'o} and
S{\"o}derg{\r{a}}rd, Lisa and
Talmoudi, Kossay and
Volodina, Elena and
Vu, Xuan-Son},
booktitle = "Proceedings of the Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Computational Approaches to Language Data Pseudonymization, Anonymization, De-identification, and Data Privacy ({LEGAL}2026 and {CALD}-pseudo 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA",
url = "https://aclanthology.org/2026.legal-1.12/",
doi = "10.63317/2spfi3ghhwaj",
pages = "102--115",
abstract = "Large Language Models (LLMs) are linked to several issues regarding Personally Identifiable Information (PII). PII can occur in the training data and can thus be accidentally leaked or extracted with malicious intent, or it can be inputted in LLM-based technologies by users through their prompts. A viable strategy to limit the LLMs' exposure to PII is to filter input and output data by de-identifying PII, including personal names. This however poses a challenge: a name could refer to a private person in a context containing sensitive information (e.g., Michelangelo is an atheist), or it could refer to a famous artist in another context (e.g., Michelangelo{'}s Sistine Chapel), and masking the latter may hinder the LLMs' capabilities in general-knowledge tasks. We tackle the problem of personal name de-identification and focus on the decision of which personal names need to be removed (and which should be kept), based on context. We present VEIL, a challenging benchmark for Value-preserving Entity Identification Limitation, for context-aware de-identification decisions on LLM training data, and compare the performance of different state-of-the-art systems on the task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gold-etal-2026-veil">
<titleInfo>
<title>VEIL: A Benchmark for Value-Preserving Entity Identification Limitation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darina</namePart>
<namePart type="family">Gold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shadi</namePart>
<namePart type="family">Rastegar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Liebel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandra</namePart>
<namePart type="family">Zarcone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Computational Approaches to Language Data Pseudonymization, Anonymization, De-identification, and Data Privacy (LEGAL2026 and CALD-pseudo 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ingo</namePart>
<namePart type="family">Siegert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Irena</namePart>
<namePart type="family">Szawerna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Kamocki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="family">Lindström Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Lison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Muñoz Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Södergård</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kossay</namePart>
<namePart type="family">Talmoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) are linked to several issues regarding Personally Identifiable Information (PII). PII can occur in the training data and can thus be accidentally leaked or extracted with malicious intent, or it can be inputted in LLM-based technologies by users through their prompts. A viable strategy to limit the LLMs’ exposure to PII is to filter input and output data by de-identifying PII, including personal names. This however poses a challenge: a name could refer to a private person in a context containing sensitive information (e.g., Michelangelo is an atheist), or it could refer to a famous artist in another context (e.g., Michelangelo’s Sistine Chapel), and masking the latter may hinder the LLMs’ capabilities in general-knowledge tasks. We tackle the problem of personal name de-identification and focus on the decision of which personal names need to be removed (and which should be kept), based on context. We present VEIL, a challenging benchmark for Value-preserving Entity Identification Limitation, for context-aware de-identification decisions on LLM training data, and compare the performance of different state-of-the-art systems on the task.</abstract>
<identifier type="citekey">gold-etal-2026-veil</identifier>
<identifier type="doi">10.63317/2spfi3ghhwaj</identifier>
<location>
<url>https://aclanthology.org/2026.legal-1.12/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>102</start>
<end>115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VEIL: A Benchmark for Value-Preserving Entity Identification Limitation
%A Gold, Darina
%A Rastegar, Shadi
%A Liebel, Alina
%A Zarcone, Alessandra
%Y Siegert, Ingo
%Y Szawerna, Maria Irena
%Y Choukri, Khalid
%Y Dobnik, Simon
%Y Kamocki, Paweł
%Y Lindström Tiedemann, Therese
%Y Lison, Pierre
%Y Muñoz Sánchez, Ricardo
%Y Pilán, Ildikó
%Y Södergård, Lisa
%Y Talmoudi, Kossay
%Y Volodina, Elena
%Y Vu, Xuan-Son
%S Proceedings of the Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Computational Approaches to Language Data Pseudonymization, Anonymization, De-identification, and Data Privacy (LEGAL2026 and CALD-pseudo 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA
%C Palma, Mallorca (Spain)
%F gold-etal-2026-veil
%X Large Language Models (LLMs) are linked to several issues regarding Personally Identifiable Information (PII). PII can occur in the training data and can thus be accidentally leaked or extracted with malicious intent, or it can be inputted in LLM-based technologies by users through their prompts. A viable strategy to limit the LLMs’ exposure to PII is to filter input and output data by de-identifying PII, including personal names. This however poses a challenge: a name could refer to a private person in a context containing sensitive information (e.g., Michelangelo is an atheist), or it could refer to a famous artist in another context (e.g., Michelangelo’s Sistine Chapel), and masking the latter may hinder the LLMs’ capabilities in general-knowledge tasks. We tackle the problem of personal name de-identification and focus on the decision of which personal names need to be removed (and which should be kept), based on context. We present VEIL, a challenging benchmark for Value-preserving Entity Identification Limitation, for context-aware de-identification decisions on LLM training data, and compare the performance of different state-of-the-art systems on the task.
%R 10.63317/2spfi3ghhwaj
%U https://aclanthology.org/2026.legal-1.12/
%U https://doi.org/10.63317/2spfi3ghhwaj
%P 102-115
Markdown (Informal)
[VEIL: A Benchmark for Value-Preserving Entity Identification Limitation](https://aclanthology.org/2026.legal-1.12/) (Gold et al., LEGAL-CALD-pseudo 2026)
ACL
- Darina Gold, Shadi Rastegar, Alina Liebel, and Alessandra Zarcone. 2026. VEIL: A Benchmark for Value-Preserving Entity Identification Limitation. In Proceedings of the Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Computational Approaches to Language Data Pseudonymization, Anonymization, De-identification, and Data Privacy (LEGAL2026 and CALD-pseudo 2026) @ LREC 2026, pages 102–115, Palma, Mallorca (Spain). ELRA.