@inproceedings{zhang-etal-2025-priority,
title = "Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection",
author = "Zhang, Hong and
Zhao, Feng and
Zhao, Ruilin and
Yan, Cheng and
Liu, Kangzheng",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1048/",
doi = "10.18653/v1/2025.emnlp-main.1048",
pages = "20764--20776",
ISBN = "979-8-89176-332-6",
abstract = "Large Language Models (LLMs) have demonstrated a remarkable understanding of language nuances through instruction tuning, enabling them to effectively tackle various natural language processing tasks. Recent research has focused on the quality of instruction data rather than the quantity of instructions. However, existing high-quality instruction selection methods rely on external models or rules, overlooking the intrinsic association between pre-trained model and instruction data, making it difficult to select data that align with the preferences of pre-trained model. To address this challenge, we propose a strategy that utilizes noise injection to identify the quality of instruction data, without relying on external model. We also implement the strategy of combining inter-class diversity and intra-class diversity to improve model performance. The experimental results demonstrate that our method significantly outperforms the model trained on the entire dataset and established baselines. Our study provides a new perspective on noise injection in the field of instruction tuning, and also illustrates that the pre-trained model itself should be considered in defining high-quality. Additionally, we publish our selected high-quality instruction data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-priority">
<titleInfo>
<title>Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruilin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kangzheng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have demonstrated a remarkable understanding of language nuances through instruction tuning, enabling them to effectively tackle various natural language processing tasks. Recent research has focused on the quality of instruction data rather than the quantity of instructions. However, existing high-quality instruction selection methods rely on external models or rules, overlooking the intrinsic association between pre-trained model and instruction data, making it difficult to select data that align with the preferences of pre-trained model. To address this challenge, we propose a strategy that utilizes noise injection to identify the quality of instruction data, without relying on external model. We also implement the strategy of combining inter-class diversity and intra-class diversity to improve model performance. The experimental results demonstrate that our method significantly outperforms the model trained on the entire dataset and established baselines. Our study provides a new perspective on noise injection in the field of instruction tuning, and also illustrates that the pre-trained model itself should be considered in defining high-quality. Additionally, we publish our selected high-quality instruction data.</abstract>
<identifier type="citekey">zhang-etal-2025-priority</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1048</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1048/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>20764</start>
<end>20776</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection
%A Zhang, Hong
%A Zhao, Feng
%A Zhao, Ruilin
%A Yan, Cheng
%A Liu, Kangzheng
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F zhang-etal-2025-priority
%X Large Language Models (LLMs) have demonstrated a remarkable understanding of language nuances through instruction tuning, enabling them to effectively tackle various natural language processing tasks. Recent research has focused on the quality of instruction data rather than the quantity of instructions. However, existing high-quality instruction selection methods rely on external models or rules, overlooking the intrinsic association between pre-trained model and instruction data, making it difficult to select data that align with the preferences of pre-trained model. To address this challenge, we propose a strategy that utilizes noise injection to identify the quality of instruction data, without relying on external model. We also implement the strategy of combining inter-class diversity and intra-class diversity to improve model performance. The experimental results demonstrate that our method significantly outperforms the model trained on the entire dataset and established baselines. Our study provides a new perspective on noise injection in the field of instruction tuning, and also illustrates that the pre-trained model itself should be considered in defining high-quality. Additionally, we publish our selected high-quality instruction data.
%R 10.18653/v1/2025.emnlp-main.1048
%U https://aclanthology.org/2025.emnlp-main.1048/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1048
%P 20764-20776
Markdown (Informal)
[Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection](https://aclanthology.org/2025.emnlp-main.1048/) (Zhang et al., EMNLP 2025)
ACL