@inproceedings{gebreegziabher-etal-2025-leveraging,
title = "Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning",
author = "Gebreegziabher, Simret A and
Ai, Kuangshi and
Zhang, Zheng and
Glassman, Elena and
Li, Toby Jia-Jun",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.50/",
doi = "10.18653/v1/2025.findings-acl.50",
pages = "894--906",
ISBN = "979-8-89176-256-5",
abstract = "Active Learning (AL) allows models to learn interactively from user feedback. However, only annotating existing samples may hardly benefit the model{'}s generalization. Moreover, AL commonly faces a cold start problem due to insufficient annotated data for effective sample selection. To address this, we introduce a counterfactual data augmentation approach inspired by Variation Theory, a theory of human concept learning that emphasizes the essential features of a concept by focusing on what stays the same and what changes. We use a neuro-symbolic pipeline to pinpoint key conceptual dimensions and use a large language model (LLM) to generate targeted variations along those dimensions. Through a text classification experiment, we show that our approach achieves significantly higher performance when there are fewer annotated data, showing its capability to address the cold start problem in AL. We also find that as the annotated training data gets larger, the impact of the generated data starts to diminish. This work demonstrates the value of incorporating human learning theories into the design and optimization of AL."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gebreegziabher-etal-2025-leveraging">
<titleInfo>
<title>Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simret</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Gebreegziabher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuangshi</namePart>
<namePart type="family">Ai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Glassman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toby</namePart>
<namePart type="given">Jia-Jun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Active Learning (AL) allows models to learn interactively from user feedback. However, only annotating existing samples may hardly benefit the model’s generalization. Moreover, AL commonly faces a cold start problem due to insufficient annotated data for effective sample selection. To address this, we introduce a counterfactual data augmentation approach inspired by Variation Theory, a theory of human concept learning that emphasizes the essential features of a concept by focusing on what stays the same and what changes. We use a neuro-symbolic pipeline to pinpoint key conceptual dimensions and use a large language model (LLM) to generate targeted variations along those dimensions. Through a text classification experiment, we show that our approach achieves significantly higher performance when there are fewer annotated data, showing its capability to address the cold start problem in AL. We also find that as the annotated training data gets larger, the impact of the generated data starts to diminish. This work demonstrates the value of incorporating human learning theories into the design and optimization of AL.</abstract>
<identifier type="citekey">gebreegziabher-etal-2025-leveraging</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.50</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.50/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>894</start>
<end>906</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning
%A Gebreegziabher, Simret A.
%A Ai, Kuangshi
%A Zhang, Zheng
%A Glassman, Elena
%A Li, Toby Jia-Jun
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F gebreegziabher-etal-2025-leveraging
%X Active Learning (AL) allows models to learn interactively from user feedback. However, only annotating existing samples may hardly benefit the model’s generalization. Moreover, AL commonly faces a cold start problem due to insufficient annotated data for effective sample selection. To address this, we introduce a counterfactual data augmentation approach inspired by Variation Theory, a theory of human concept learning that emphasizes the essential features of a concept by focusing on what stays the same and what changes. We use a neuro-symbolic pipeline to pinpoint key conceptual dimensions and use a large language model (LLM) to generate targeted variations along those dimensions. Through a text classification experiment, we show that our approach achieves significantly higher performance when there are fewer annotated data, showing its capability to address the cold start problem in AL. We also find that as the annotated training data gets larger, the impact of the generated data starts to diminish. This work demonstrates the value of incorporating human learning theories into the design and optimization of AL.
%R 10.18653/v1/2025.findings-acl.50
%U https://aclanthology.org/2025.findings-acl.50/
%U https://doi.org/10.18653/v1/2025.findings-acl.50
%P 894-906
Markdown (Informal)
[Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning](https://aclanthology.org/2025.findings-acl.50/) (Gebreegziabher et al., Findings 2025)
ACL