<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bayer-etal-2026-activellm">
    <titleInfo>
        <title>ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Markus</namePart>
        <namePart type="family">Bayer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Justin</namePart>
        <namePart type="family">Lutz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christian</namePart>
        <namePart type="family">Reuter</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Active learning is designed to minimize annotation efforts by prioritizing instances that most enhance learning. However, many active learning strategies struggle with a ‘cold-start’ problem, needing substantial initial data to be effective. This limitation reduces their utility in the increasingly relevant few-shot scenarios, where the instance selection has a substantial impact. To address this, we introduce ActiveLLM, a novel active learning approach that leverages Large Language Models such as GPT-4, o1, Llama 3, or Mistral Large for selecting instances. We demonstrate that ActiveLLM significantly enhances the classification performance of BERT classifiers in few-shot scenarios, outperforming traditional active learning methods as well as improving the few-shot learning methods ADAPET, PERFECT, and SetFit. Additionally, ActiveLLM can be extended to non-few-shot scenarios, allowing for iterative selections. In this way, ActiveLLM can even help other active learning strategies to overcome their cold-start problem. Our results suggest that ActiveLLM offers a promising solution for improving model performance across various learning setups.</abstract>
    <identifier type="citekey">bayer-etal-2026-activellm</identifier>
    <identifier type="doi">10.1162/tacl.a.63</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.1/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>1</start>
            <end>22</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios
%A Bayer, Markus
%A Lutz, Justin
%A Reuter, Christian
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F bayer-etal-2026-activellm
%X Active learning is designed to minimize annotation efforts by prioritizing instances that most enhance learning. However, many active learning strategies struggle with a ‘cold-start’ problem, needing substantial initial data to be effective. This limitation reduces their utility in the increasingly relevant few-shot scenarios, where the instance selection has a substantial impact. To address this, we introduce ActiveLLM, a novel active learning approach that leverages Large Language Models such as GPT-4, o1, Llama 3, or Mistral Large for selecting instances. We demonstrate that ActiveLLM significantly enhances the classification performance of BERT classifiers in few-shot scenarios, outperforming traditional active learning methods as well as improving the few-shot learning methods ADAPET, PERFECT, and SetFit. Additionally, ActiveLLM can be extended to non-few-shot scenarios, allowing for iterative selections. In this way, ActiveLLM can even help other active learning strategies to overcome their cold-start problem. Our results suggest that ActiveLLM offers a promising solution for improving model performance across various learning setups.
%R 10.1162/tacl.a.63
%U https://aclanthology.org/2026.tacl-1.1/
%U https://doi.org/10.1162/tacl.a.63
%P 1-22

Markdown (Informal)

[ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios](https://aclanthology.org/2026.tacl-1.1/) (Bayer et al., TACL 2026)

• ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios (Bayer et al., TACL 2026)

ACL

• Markus Bayer, Justin Lutz, and Christian Reuter. 2026. ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios. Transactions of the Association for Computational Linguistics, 14:1–22.