@inproceedings{liu-etal-2026-knowledge-control,
title = "Knowledge Control for Responsible Generative {AI}: Bridging Academia, Industry, and Society",
author = "Liu, Zheyuan and
Wan, Yixin and
Chang, Kai-Wei and
Jiang, Meng and
Zhao, Jieyu and
Dziri, Nouha and
Mao, Yuning and
Gu, Jia-Chen and
Gu, Jindong",
editor = "Andreas, Jacob and
Murray, Kenton",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Tutorial Abstracts)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-tutorials.5/",
pages = "9--10",
ISBN = "979-8-89176-394-4",
abstract = "Controlling the knowledge and behavior of generative AI systems, including large language models (LLMs), multimodal LLMs (MLLMs), and text-to-image (T2I) models, has become critical as they are increasingly used in safety-sensitive and socially impactful applications. These models often encode unintended, biased, or private content, leading to harmful or unethical outputs. Post-training knowledge control has thus emerged as a practical framework for selectively modifying or removing model behaviors without full retraining, offering scalable and interpretable interventions for improving safety, privacy, and fairness. This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods, bridging research insights with real-world practices from both academia and industry. We cover: (i) key motivations and failure modes, such as harmful generation and stereotype reinforcement; (ii) core methods such as machine unlearning, knowledge editing, and inference-time interventions for targeted behavior adjustment; and (iii) evaluation protocols for balancing forgetting, retention, and fairness. Case studies will span text and vision{--}language generation, including privacy preservation, bias mitigation, and factual correction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-knowledge-control">
<titleInfo>
<title>Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nouha</namePart>
<namePart type="family">Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuning</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia-Chen</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jindong</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Andreas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenton</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Controlling the knowledge and behavior of generative AI systems, including large language models (LLMs), multimodal LLMs (MLLMs), and text-to-image (T2I) models, has become critical as they are increasingly used in safety-sensitive and socially impactful applications. These models often encode unintended, biased, or private content, leading to harmful or unethical outputs. Post-training knowledge control has thus emerged as a practical framework for selectively modifying or removing model behaviors without full retraining, offering scalable and interpretable interventions for improving safety, privacy, and fairness. This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods, bridging research insights with real-world practices from both academia and industry. We cover: (i) key motivations and failure modes, such as harmful generation and stereotype reinforcement; (ii) core methods such as machine unlearning, knowledge editing, and inference-time interventions for targeted behavior adjustment; and (iii) evaluation protocols for balancing forgetting, retention, and fairness. Case studies will span text and vision–language generation, including privacy preservation, bias mitigation, and factual correction.</abstract>
<identifier type="citekey">liu-etal-2026-knowledge-control</identifier>
<location>
<url>https://aclanthology.org/2026.acl-tutorials.5/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>9</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society
%A Liu, Zheyuan
%A Wan, Yixin
%A Chang, Kai-Wei
%A Jiang, Meng
%A Zhao, Jieyu
%A Dziri, Nouha
%A Mao, Yuning
%A Gu, Jia-Chen
%A Gu, Jindong
%Y Andreas, Jacob
%Y Murray, Kenton
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F liu-etal-2026-knowledge-control
%X Controlling the knowledge and behavior of generative AI systems, including large language models (LLMs), multimodal LLMs (MLLMs), and text-to-image (T2I) models, has become critical as they are increasingly used in safety-sensitive and socially impactful applications. These models often encode unintended, biased, or private content, leading to harmful or unethical outputs. Post-training knowledge control has thus emerged as a practical framework for selectively modifying or removing model behaviors without full retraining, offering scalable and interpretable interventions for improving safety, privacy, and fairness. This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods, bridging research insights with real-world practices from both academia and industry. We cover: (i) key motivations and failure modes, such as harmful generation and stereotype reinforcement; (ii) core methods such as machine unlearning, knowledge editing, and inference-time interventions for targeted behavior adjustment; and (iii) evaluation protocols for balancing forgetting, retention, and fairness. Case studies will span text and vision–language generation, including privacy preservation, bias mitigation, and factual correction.
%U https://aclanthology.org/2026.acl-tutorials.5/
%P 9-10
Markdown (Informal)
[Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society](https://aclanthology.org/2026.acl-tutorials.5/) (Liu et al., ACL 2026)
ACL
- Zheyuan Liu, Yixin Wan, Kai-Wei Chang, Meng Jiang, Jieyu Zhao, Nouha Dziri, Yuning Mao, Jia-Chen Gu, and Jindong Gu. 2026. Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts), pages 9–10, San Diego, California, USA. Association for Computational Linguistics.