@inproceedings{kang-etal-2026-r,
title = "{R}-{GDA}: Reflective Guidance Data Augmentation with Multi-Agent Feedback for Domain-Specific Named Entity Recognition",
author = "Kang, Hyeonseok and
Namgoong, Hyuk and
Pyeon, Goun and
Jung, Sangkeun",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.259/",
pages = "4938--4953",
ISBN = "979-8-89176-386-9",
abstract = "Domain-specific Named Entity Recognition (NER) often requires data augmentation due to the scarcity of annotated corpora. Guidance Data Augmentation (GDA), a method utilizing Large Language Models (LLMs) to decompose sentences into abstract components, can lead to over-abstraction, resulting in undefined entity tags and sentences lacking domain-specific vocabulary. In this work, we propose Reflective GDA (R-GDA), a framework that introduces a multi-agent feedback loop to enhance augmentation quality. R-GDA incorporates two distinct agents: a **Guidance Refiner (GR)**, which assesses the initial abstraction to prevent over-generalization, and an **Augmentation Calibrator (AC)**, which validates the final generated sample for domain-fidelity and tag integrity. On the SciERC and NCBI-disease datasets, R-GDA improves F1-Score, validating its effectiveness. Concurrently, it achieves low BERTScore in most cases, indicating greater sentence diversity. For the FIN dataset, it achieves performance comparable to the GDA baseline. R-GDA consistently prevents errors regarding domain-specific tags, demonstrating that the reflective feedback mechanism enhances data fidelity by mitigating critical generation errors."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2026-r">
<titleInfo>
<title>R-GDA: Reflective Guidance Data Augmentation with Multi-Agent Feedback for Domain-Specific Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyeonseok</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyuk</namePart>
<namePart type="family">Namgoong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goun</namePart>
<namePart type="family">Pyeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sangkeun</namePart>
<namePart type="family">Jung</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>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</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">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Domain-specific Named Entity Recognition (NER) often requires data augmentation due to the scarcity of annotated corpora. Guidance Data Augmentation (GDA), a method utilizing Large Language Models (LLMs) to decompose sentences into abstract components, can lead to over-abstraction, resulting in undefined entity tags and sentences lacking domain-specific vocabulary. In this work, we propose Reflective GDA (R-GDA), a framework that introduces a multi-agent feedback loop to enhance augmentation quality. R-GDA incorporates two distinct agents: a **Guidance Refiner (GR)**, which assesses the initial abstraction to prevent over-generalization, and an **Augmentation Calibrator (AC)**, which validates the final generated sample for domain-fidelity and tag integrity. On the SciERC and NCBI-disease datasets, R-GDA improves F1-Score, validating its effectiveness. Concurrently, it achieves low BERTScore in most cases, indicating greater sentence diversity. For the FIN dataset, it achieves performance comparable to the GDA baseline. R-GDA consistently prevents errors regarding domain-specific tags, demonstrating that the reflective feedback mechanism enhances data fidelity by mitigating critical generation errors.</abstract>
<identifier type="citekey">kang-etal-2026-r</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.259/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4938</start>
<end>4953</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T R-GDA: Reflective Guidance Data Augmentation with Multi-Agent Feedback for Domain-Specific Named Entity Recognition
%A Kang, Hyeonseok
%A Namgoong, Hyuk
%A Pyeon, Goun
%A Jung, Sangkeun
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F kang-etal-2026-r
%X Domain-specific Named Entity Recognition (NER) often requires data augmentation due to the scarcity of annotated corpora. Guidance Data Augmentation (GDA), a method utilizing Large Language Models (LLMs) to decompose sentences into abstract components, can lead to over-abstraction, resulting in undefined entity tags and sentences lacking domain-specific vocabulary. In this work, we propose Reflective GDA (R-GDA), a framework that introduces a multi-agent feedback loop to enhance augmentation quality. R-GDA incorporates two distinct agents: a **Guidance Refiner (GR)**, which assesses the initial abstraction to prevent over-generalization, and an **Augmentation Calibrator (AC)**, which validates the final generated sample for domain-fidelity and tag integrity. On the SciERC and NCBI-disease datasets, R-GDA improves F1-Score, validating its effectiveness. Concurrently, it achieves low BERTScore in most cases, indicating greater sentence diversity. For the FIN dataset, it achieves performance comparable to the GDA baseline. R-GDA consistently prevents errors regarding domain-specific tags, demonstrating that the reflective feedback mechanism enhances data fidelity by mitigating critical generation errors.
%U https://aclanthology.org/2026.findings-eacl.259/
%P 4938-4953
Markdown (Informal)
[R-GDA: Reflective Guidance Data Augmentation with Multi-Agent Feedback for Domain-Specific Named Entity Recognition](https://aclanthology.org/2026.findings-eacl.259/) (Kang et al., Findings 2026)
ACL