@inproceedings{yuan-etal-2026-divide,
title = "Divide, Conquer, and Distill: Unified Sample Selection and {LLM} Distillation for Noisy Long-Tailed Learning",
author = "Yuan, Bo and
Chen, Yulin and
Cao, Jie and
Gao, Mei",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1447/",
pages = "30847--30864",
ISBN = "979-8-89176-462-0",
abstract = "There is a rising interest in further exploring learning with noisy labels on textual data. Existing solutions often assume the ground truth classes of the training data are balanced, overlooking the long-tailed distribution prevalently encountered in real-world data, which can significantly harm the effect of denoising strategies. Meanwhile, misidentifying clean samples further compromises the model{'}s learning of long-tailed data. To tackle this issue, we propose a novel knowledge distillation framework for learning with noisy labels under long-tailed distribution (LNL-LT). Specifically, we first introduce a divide-and-conquer sample selection strategy to perform head-tail class division and better separate clean samples from noisy samples within these classes, especially for the tail classes. Then, we employ LLM knowledge distillation to generate pseudo-labels and new samples for tail classes, enhancing pseudo-label quality while mitigating the effects of sample scarcity caused by the long-tailed distribution. Experimental results on both synthetic and real-world datasets demonstrate that our method surpasses current state-of-the-art methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2026-divide">
<titleInfo>
<title>Divide, Conquer, and Distill: Unified Sample Selection and LLM Distillation for Noisy Long-Tailed Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>There is a rising interest in further exploring learning with noisy labels on textual data. Existing solutions often assume the ground truth classes of the training data are balanced, overlooking the long-tailed distribution prevalently encountered in real-world data, which can significantly harm the effect of denoising strategies. Meanwhile, misidentifying clean samples further compromises the model’s learning of long-tailed data. To tackle this issue, we propose a novel knowledge distillation framework for learning with noisy labels under long-tailed distribution (LNL-LT). Specifically, we first introduce a divide-and-conquer sample selection strategy to perform head-tail class division and better separate clean samples from noisy samples within these classes, especially for the tail classes. Then, we employ LLM knowledge distillation to generate pseudo-labels and new samples for tail classes, enhancing pseudo-label quality while mitigating the effects of sample scarcity caused by the long-tailed distribution. Experimental results on both synthetic and real-world datasets demonstrate that our method surpasses current state-of-the-art methods.</abstract>
<identifier type="citekey">yuan-etal-2026-divide</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1447/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>30847</start>
<end>30864</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Divide, Conquer, and Distill: Unified Sample Selection and LLM Distillation for Noisy Long-Tailed Learning
%A Yuan, Bo
%A Chen, Yulin
%A Cao, Jie
%A Gao, Mei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F yuan-etal-2026-divide
%X There is a rising interest in further exploring learning with noisy labels on textual data. Existing solutions often assume the ground truth classes of the training data are balanced, overlooking the long-tailed distribution prevalently encountered in real-world data, which can significantly harm the effect of denoising strategies. Meanwhile, misidentifying clean samples further compromises the model’s learning of long-tailed data. To tackle this issue, we propose a novel knowledge distillation framework for learning with noisy labels under long-tailed distribution (LNL-LT). Specifically, we first introduce a divide-and-conquer sample selection strategy to perform head-tail class division and better separate clean samples from noisy samples within these classes, especially for the tail classes. Then, we employ LLM knowledge distillation to generate pseudo-labels and new samples for tail classes, enhancing pseudo-label quality while mitigating the effects of sample scarcity caused by the long-tailed distribution. Experimental results on both synthetic and real-world datasets demonstrate that our method surpasses current state-of-the-art methods.
%U https://aclanthology.org/2026.findings-emnlp.1447/
%P 30847-30864
Markdown (Informal)
[Divide, Conquer, and Distill: Unified Sample Selection and LLM Distillation for Noisy Long-Tailed Learning](https://aclanthology.org/2026.findings-emnlp.1447/) (Yuan et al., Findings 2026)
ACL