@inproceedings{shlyk-etal-2026-mind,
title = "Mind Your Steps in Biomedical Named Entity Recognition: First Extract, Tag Afterwards",
author = "Shlyk, Darya and
Montanelli, Stefano and
Mesiti, Marco and
Hunter, Lawrence",
editor = {Danilova, Vera and
Kurfal{\i}, Murathan and
S{\"o}derfeldt, Ylva and
Reed, Julia and
Burchell, Andrew},
booktitle = "Proceedings of the 1st Workshop on Linguistic Analysis for Health ({H}ea{L}ing 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.healing-1.11/",
pages = "127--141",
ISBN = "979-8-89176-367-8",
abstract = "Few-shot prompting with Large Language Models (LLMs) has emerged as a promising paradigm for advancing information extraction, particularly in data-scarce domains like biomedicine, where high annotation costs constrain the availability of training data.However, challenges persist in biomedical Named Entity Recognition (NER), where LLMs fail to achieve necessary accuracy and lag behind supervised fine-tuned models. In this study, we introduce FETA (\textit{First Extract, Tag Afterwards}), a two-stage approach for entity recognition that combines instruction-guided prompting and a novel self-verification strategy to improve accuracy and reliability of LLM predictions in domain-specific NER tasks. FETA achieves state-of-the-art results on multiple established biomedical datasets.Our experiments demonstrate that carefully designed prompts, using self-verification and instruction guidance, can steer general-purpose LLMs to outperform fine-tuned models in knowledge-intensive NER tasks, unlocking their potential for more reliable and accurate information extraction in resource-constrained settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shlyk-etal-2026-mind">
<titleInfo>
<title>Mind Your Steps in Biomedical Named Entity Recognition: First Extract, Tag Afterwards</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darya</namePart>
<namePart type="family">Shlyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Montanelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Mesiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Hunter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Danilova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Murathan</namePart>
<namePart type="family">Kurfalı</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ylva</namePart>
<namePart type="family">Söderfeldt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Reed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Burchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-367-8</identifier>
</relatedItem>
<abstract>Few-shot prompting with Large Language Models (LLMs) has emerged as a promising paradigm for advancing information extraction, particularly in data-scarce domains like biomedicine, where high annotation costs constrain the availability of training data.However, challenges persist in biomedical Named Entity Recognition (NER), where LLMs fail to achieve necessary accuracy and lag behind supervised fine-tuned models. In this study, we introduce FETA (First Extract, Tag Afterwards), a two-stage approach for entity recognition that combines instruction-guided prompting and a novel self-verification strategy to improve accuracy and reliability of LLM predictions in domain-specific NER tasks. FETA achieves state-of-the-art results on multiple established biomedical datasets.Our experiments demonstrate that carefully designed prompts, using self-verification and instruction guidance, can steer general-purpose LLMs to outperform fine-tuned models in knowledge-intensive NER tasks, unlocking their potential for more reliable and accurate information extraction in resource-constrained settings.</abstract>
<identifier type="citekey">shlyk-etal-2026-mind</identifier>
<location>
<url>https://aclanthology.org/2026.healing-1.11/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>127</start>
<end>141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mind Your Steps in Biomedical Named Entity Recognition: First Extract, Tag Afterwards
%A Shlyk, Darya
%A Montanelli, Stefano
%A Mesiti, Marco
%A Hunter, Lawrence
%Y Danilova, Vera
%Y Kurfalı, Murathan
%Y Söderfeldt, Ylva
%Y Reed, Julia
%Y Burchell, Andrew
%S Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-367-8
%F shlyk-etal-2026-mind
%X Few-shot prompting with Large Language Models (LLMs) has emerged as a promising paradigm for advancing information extraction, particularly in data-scarce domains like biomedicine, where high annotation costs constrain the availability of training data.However, challenges persist in biomedical Named Entity Recognition (NER), where LLMs fail to achieve necessary accuracy and lag behind supervised fine-tuned models. In this study, we introduce FETA (First Extract, Tag Afterwards), a two-stage approach for entity recognition that combines instruction-guided prompting and a novel self-verification strategy to improve accuracy and reliability of LLM predictions in domain-specific NER tasks. FETA achieves state-of-the-art results on multiple established biomedical datasets.Our experiments demonstrate that carefully designed prompts, using self-verification and instruction guidance, can steer general-purpose LLMs to outperform fine-tuned models in knowledge-intensive NER tasks, unlocking their potential for more reliable and accurate information extraction in resource-constrained settings.
%U https://aclanthology.org/2026.healing-1.11/
%P 127-141
Markdown (Informal)
[Mind Your Steps in Biomedical Named Entity Recognition: First Extract, Tag Afterwards](https://aclanthology.org/2026.healing-1.11/) (Shlyk et al., HeaLing 2026)
ACL