@inproceedings{shalchian-etal-2026-persiananonymizer,
title = "{P}ersian{A}nonymizer: Evaluating {LLM}-Labeled Training for Efficient {NER}-based Anonymization in {P}ersian",
author = "Shalchian, Mohammad Hossein and
Amiri, Mostafa and
Sadeghzadeh, Amir Mahdi",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.352/",
doi = "10.63317/57u2ica9225o",
pages = "4497--4506",
abstract = "We target practical anonymization of Persian customer chats by training a compact NER model from LLM-labeled supervision and selecting the best labeler for deployment. We compare three instruction-tuned LLMs{---}DEEPSEEKV3-0324, GPT-OSS-120B, and QWEN3-235B-A22B-INSTRUCT-2507{---}to produce span annotations under a shared JSON protocol, yielding four corpora (OSS{\_}ZeroShot, Qwen{\_}ZeroShot, Qwen{\_}FewShot, DeepSeek{\_}FewShot). A MATINAROBERTA-based token-classifier is trained per corpus and evaluated with token-level Precision/Recall/F1 (overall and per-class). We also report Label Coverage Recall (LCR), the proportion of gold non-O tokens predicted as non-O, and quantify cross-labeler behavior via a token-level Venn on test annotations. Finally, we contrast test-set annotation latency of the LLMs on H200 nodes with the trained NER{'}s test-time labeling on a single RTX 3090. Results show that supervision from OSS{\_}ZeroShot yields the strongest macro-F1 and LCR, while the resulting NER labels an entire 40K-message test set in {\ensuremath{\sim}}2 minutes on one consumer GPU. This establishes a practical path to high-quality, low-cost anonymization for Persian industrial data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shalchian-etal-2026-persiananonymizer">
<titleInfo>
<title>PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Shalchian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mostafa</namePart>
<namePart type="family">Amiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="given">Mahdi</namePart>
<namePart type="family">Sadeghzadeh</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We target practical anonymization of Persian customer chats by training a compact NER model from LLM-labeled supervision and selecting the best labeler for deployment. We compare three instruction-tuned LLMs—DEEPSEEKV3-0324, GPT-OSS-120B, and QWEN3-235B-A22B-INSTRUCT-2507—to produce span annotations under a shared JSON protocol, yielding four corpora (OSS_ZeroShot, Qwen_ZeroShot, Qwen_FewShot, DeepSeek_FewShot). A MATINAROBERTA-based token-classifier is trained per corpus and evaluated with token-level Precision/Recall/F1 (overall and per-class). We also report Label Coverage Recall (LCR), the proportion of gold non-O tokens predicted as non-O, and quantify cross-labeler behavior via a token-level Venn on test annotations. Finally, we contrast test-set annotation latency of the LLMs on H200 nodes with the trained NER’s test-time labeling on a single RTX 3090. Results show that supervision from OSS_ZeroShot yields the strongest macro-F1 and LCR, while the resulting NER labels an entire 40K-message test set in \ensuremath\sim2 minutes on one consumer GPU. This establishes a practical path to high-quality, low-cost anonymization for Persian industrial data.</abstract>
<identifier type="citekey">shalchian-etal-2026-persiananonymizer</identifier>
<identifier type="doi">10.63317/57u2ica9225o</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.352/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4497</start>
<end>4506</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian
%A Shalchian, Mohammad Hossein
%A Amiri, Mostafa
%A Sadeghzadeh, Amir Mahdi
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F shalchian-etal-2026-persiananonymizer
%X We target practical anonymization of Persian customer chats by training a compact NER model from LLM-labeled supervision and selecting the best labeler for deployment. We compare three instruction-tuned LLMs—DEEPSEEKV3-0324, GPT-OSS-120B, and QWEN3-235B-A22B-INSTRUCT-2507—to produce span annotations under a shared JSON protocol, yielding four corpora (OSS_ZeroShot, Qwen_ZeroShot, Qwen_FewShot, DeepSeek_FewShot). A MATINAROBERTA-based token-classifier is trained per corpus and evaluated with token-level Precision/Recall/F1 (overall and per-class). We also report Label Coverage Recall (LCR), the proportion of gold non-O tokens predicted as non-O, and quantify cross-labeler behavior via a token-level Venn on test annotations. Finally, we contrast test-set annotation latency of the LLMs on H200 nodes with the trained NER’s test-time labeling on a single RTX 3090. Results show that supervision from OSS_ZeroShot yields the strongest macro-F1 and LCR, while the resulting NER labels an entire 40K-message test set in \ensuremath\sim2 minutes on one consumer GPU. This establishes a practical path to high-quality, low-cost anonymization for Persian industrial data.
%R 10.63317/57u2ica9225o
%U https://aclanthology.org/2026.lrec-1.352/
%U https://doi.org/10.63317/57u2ica9225o
%P 4497-4506
Markdown (Informal)
[PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian](https://aclanthology.org/2026.lrec-1.352/) (Shalchian et al., LREC 2026)
ACL