@inproceedings{mamooler-etal-2025-picle,
title = "{PICL}e: Pseudo-annotations for In-Context Learning in Low-Resource Named Entity Detection",
author = "Mamooler, Sepideh and
Montariol, Syrielle and
Mathis, Alexander and
Bosselut, Antoine",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.518/",
doi = "10.18653/v1/2025.naacl-long.518",
pages = "10314--10331",
ISBN = "979-8-89176-189-6",
abstract = "In-context learning (ICL) enables Large Language Models (LLMs) to perform tasks using few demonstrations, facilitating task adaptation when labeled examples are hard to come by. However, ICL is sensitive to the choice of demonstrations, and it remains unclear which demonstration attributes enable in-context generalization. In this work, we conduct a perturbation study of in-context demonstrations for low-resource Named Entity Detection (NED). Our surprising finding is that in-context demonstrations with partially-correct annotated entity mentions can be as effective for task transfer as fully correct demonstrations. Based off our findings, we propose Pseudo-annotated In-Context Learning (PICLe), a framework for in-context learning with noisy, pseudo-annotated demonstrations. PICLe leverages LLMs to annotate large quantities of demonstrations in a zero-shot first pass. We then cluster these synthetic demonstrations, sample specific sets of in-context demonstrations from each cluster, and predict entity mentions using each set independently. Finally, we use self-verification to select the final set of entity mentions. We extensively evaluate PICLe on five biomedical NED datasets and show that, with zero human-annotation, PICLe outperforms ICL in low-resource settings where few gold examples can be used as in-context demonstrations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mamooler-etal-2025-picle">
<titleInfo>
<title>PICLe: Pseudo-annotations for In-Context Learning in Low-Resource Named Entity Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sepideh</namePart>
<namePart type="family">Mamooler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Mathis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>In-context learning (ICL) enables Large Language Models (LLMs) to perform tasks using few demonstrations, facilitating task adaptation when labeled examples are hard to come by. However, ICL is sensitive to the choice of demonstrations, and it remains unclear which demonstration attributes enable in-context generalization. In this work, we conduct a perturbation study of in-context demonstrations for low-resource Named Entity Detection (NED). Our surprising finding is that in-context demonstrations with partially-correct annotated entity mentions can be as effective for task transfer as fully correct demonstrations. Based off our findings, we propose Pseudo-annotated In-Context Learning (PICLe), a framework for in-context learning with noisy, pseudo-annotated demonstrations. PICLe leverages LLMs to annotate large quantities of demonstrations in a zero-shot first pass. We then cluster these synthetic demonstrations, sample specific sets of in-context demonstrations from each cluster, and predict entity mentions using each set independently. Finally, we use self-verification to select the final set of entity mentions. We extensively evaluate PICLe on five biomedical NED datasets and show that, with zero human-annotation, PICLe outperforms ICL in low-resource settings where few gold examples can be used as in-context demonstrations.</abstract>
<identifier type="citekey">mamooler-etal-2025-picle</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.518</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.518/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>10314</start>
<end>10331</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PICLe: Pseudo-annotations for In-Context Learning in Low-Resource Named Entity Detection
%A Mamooler, Sepideh
%A Montariol, Syrielle
%A Mathis, Alexander
%A Bosselut, Antoine
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F mamooler-etal-2025-picle
%X In-context learning (ICL) enables Large Language Models (LLMs) to perform tasks using few demonstrations, facilitating task adaptation when labeled examples are hard to come by. However, ICL is sensitive to the choice of demonstrations, and it remains unclear which demonstration attributes enable in-context generalization. In this work, we conduct a perturbation study of in-context demonstrations for low-resource Named Entity Detection (NED). Our surprising finding is that in-context demonstrations with partially-correct annotated entity mentions can be as effective for task transfer as fully correct demonstrations. Based off our findings, we propose Pseudo-annotated In-Context Learning (PICLe), a framework for in-context learning with noisy, pseudo-annotated demonstrations. PICLe leverages LLMs to annotate large quantities of demonstrations in a zero-shot first pass. We then cluster these synthetic demonstrations, sample specific sets of in-context demonstrations from each cluster, and predict entity mentions using each set independently. Finally, we use self-verification to select the final set of entity mentions. We extensively evaluate PICLe on five biomedical NED datasets and show that, with zero human-annotation, PICLe outperforms ICL in low-resource settings where few gold examples can be used as in-context demonstrations.
%R 10.18653/v1/2025.naacl-long.518
%U https://aclanthology.org/2025.naacl-long.518/
%U https://doi.org/10.18653/v1/2025.naacl-long.518
%P 10314-10331
Markdown (Informal)
[PICLe: Pseudo-annotations for In-Context Learning in Low-Resource Named Entity Detection](https://aclanthology.org/2025.naacl-long.518/) (Mamooler et al., NAACL 2025)
ACL
- Sepideh Mamooler, Syrielle Montariol, Alexander Mathis, and Antoine Bosselut. 2025. PICLe: Pseudo-annotations for In-Context Learning in Low-Resource Named Entity Detection. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 10314–10331, Albuquerque, New Mexico. Association for Computational Linguistics.