@inproceedings{zhang-etal-2025-self-tuning,
title = "Self-Tuning: Instructing {LLM}s to Effectively Acquire New Knowledge through Self-Teaching",
author = "Zhang, Xiaoying and
Peng, Baolin and
Tian, Ye and
Zhou, Jingyan and
Zhang, Yipeng and
Mi, Haitao and
Meng, Helen M.",
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.297/",
doi = "10.18653/v1/2025.findings-acl.297",
pages = "5688--5724",
ISBN = "979-8-89176-256-5",
abstract = "Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve continued pre-training on new documents. However, they frequently face difficulties in extracting stored knowledge. Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM{'}s ability to effectively acquire new knowledge from unseen raw documents through self-teaching. Specifically, we develop a Self-Teaching strategy that augments the documents with a set of knowledge-intensive tasks created in a self-supervised manner, focusing on three crucial aspects: memorization, comprehension, and self-reflection. Additionally, we introduce three Wiki-Newpages-2023-QA datasets to facilitate an in-depth analysis of an LLM{'}s knowledge acquisition ability concerning memorization, extraction, and reasoning. Extensive experimental results on various models, e.g., Llama2-7B reveal that Self-Tuning consistently exhibits superior performance across all knowledge acquisition tasks and excels in preserving previous knowledge."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-self-tuning">
<titleInfo>
<title>Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baolin</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yipeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitao</namePart>
<namePart type="family">Mi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Meng</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) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve continued pre-training on new documents. However, they frequently face difficulties in extracting stored knowledge. Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM’s ability to effectively acquire new knowledge from unseen raw documents through self-teaching. Specifically, we develop a Self-Teaching strategy that augments the documents with a set of knowledge-intensive tasks created in a self-supervised manner, focusing on three crucial aspects: memorization, comprehension, and self-reflection. Additionally, we introduce three Wiki-Newpages-2023-QA datasets to facilitate an in-depth analysis of an LLM’s knowledge acquisition ability concerning memorization, extraction, and reasoning. Extensive experimental results on various models, e.g., Llama2-7B reveal that Self-Tuning consistently exhibits superior performance across all knowledge acquisition tasks and excels in preserving previous knowledge.</abstract>
<identifier type="citekey">zhang-etal-2025-self-tuning</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.297</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.297/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>5688</start>
<end>5724</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
%A Zhang, Xiaoying
%A Peng, Baolin
%A Tian, Ye
%A Zhou, Jingyan
%A Zhang, Yipeng
%A Mi, Haitao
%A Meng, Helen M.
%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 zhang-etal-2025-self-tuning
%X Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve continued pre-training on new documents. However, they frequently face difficulties in extracting stored knowledge. Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM’s ability to effectively acquire new knowledge from unseen raw documents through self-teaching. Specifically, we develop a Self-Teaching strategy that augments the documents with a set of knowledge-intensive tasks created in a self-supervised manner, focusing on three crucial aspects: memorization, comprehension, and self-reflection. Additionally, we introduce three Wiki-Newpages-2023-QA datasets to facilitate an in-depth analysis of an LLM’s knowledge acquisition ability concerning memorization, extraction, and reasoning. Extensive experimental results on various models, e.g., Llama2-7B reveal that Self-Tuning consistently exhibits superior performance across all knowledge acquisition tasks and excels in preserving previous knowledge.
%R 10.18653/v1/2025.findings-acl.297
%U https://aclanthology.org/2025.findings-acl.297/
%U https://doi.org/10.18653/v1/2025.findings-acl.297
%P 5688-5724
Markdown (Informal)
[Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching](https://aclanthology.org/2025.findings-acl.297/) (Zhang et al., Findings 2025)
ACL