@inproceedings{li-etal-2025-self-foveate,
title = "Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation",
author = "Li, Mingzhe and
Lu, Xin and
Zhao, Yanyan",
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.380/",
doi = "10.18653/v1/2025.findings-acl.380",
pages = "7274--7289",
ISBN = "979-8-89176-256-5",
abstract = "Large language models (LLMs) with instruction following capabilities have demonstrated impressive problem-solving abilities. While synthesizing instructional data from unsupervised text has become a common approach for training such models, conventional methods rely heavily on human effort for data annotation. Although existing automated synthesis paradigms have alleviated this constraint, they still exhibit significant limitations in ensuring adequate diversity and difficulty of synthesized instructions. To address these challenges, we propose Self-Foveate, an innovative LLM-driven method for instruction synthesis. This approach introduces a ``Micro-Scatter-Macro'' multi-level foveation methodology that effectively guides the LLM to deeply excavate fine-grained information embedded in unsupervised text, thereby enhancing both the diversity and difficulty of synthesized instructions. Comprehensive experiments across multiple unsupervised corpora and diverse model architectures validate the effectiveness and superiority of our proposed method. We publicly release our data and codes: https://github.com/Mubuky/Self-Foveate"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-self-foveate">
<titleInfo>
<title>Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingzhe</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyan</namePart>
<namePart type="family">Zhao</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>Large language models (LLMs) with instruction following capabilities have demonstrated impressive problem-solving abilities. While synthesizing instructional data from unsupervised text has become a common approach for training such models, conventional methods rely heavily on human effort for data annotation. Although existing automated synthesis paradigms have alleviated this constraint, they still exhibit significant limitations in ensuring adequate diversity and difficulty of synthesized instructions. To address these challenges, we propose Self-Foveate, an innovative LLM-driven method for instruction synthesis. This approach introduces a “Micro-Scatter-Macro” multi-level foveation methodology that effectively guides the LLM to deeply excavate fine-grained information embedded in unsupervised text, thereby enhancing both the diversity and difficulty of synthesized instructions. Comprehensive experiments across multiple unsupervised corpora and diverse model architectures validate the effectiveness and superiority of our proposed method. We publicly release our data and codes: https://github.com/Mubuky/Self-Foveate</abstract>
<identifier type="citekey">li-etal-2025-self-foveate</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.380</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.380/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>7274</start>
<end>7289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation
%A Li, Mingzhe
%A Lu, Xin
%A Zhao, Yanyan
%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 li-etal-2025-self-foveate
%X Large language models (LLMs) with instruction following capabilities have demonstrated impressive problem-solving abilities. While synthesizing instructional data from unsupervised text has become a common approach for training such models, conventional methods rely heavily on human effort for data annotation. Although existing automated synthesis paradigms have alleviated this constraint, they still exhibit significant limitations in ensuring adequate diversity and difficulty of synthesized instructions. To address these challenges, we propose Self-Foveate, an innovative LLM-driven method for instruction synthesis. This approach introduces a “Micro-Scatter-Macro” multi-level foveation methodology that effectively guides the LLM to deeply excavate fine-grained information embedded in unsupervised text, thereby enhancing both the diversity and difficulty of synthesized instructions. Comprehensive experiments across multiple unsupervised corpora and diverse model architectures validate the effectiveness and superiority of our proposed method. We publicly release our data and codes: https://github.com/Mubuky/Self-Foveate
%R 10.18653/v1/2025.findings-acl.380
%U https://aclanthology.org/2025.findings-acl.380/
%U https://doi.org/10.18653/v1/2025.findings-acl.380
%P 7274-7289
Markdown (Informal)
[Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation](https://aclanthology.org/2025.findings-acl.380/) (Li et al., Findings 2025)
ACL