@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://preview.aclanthology.org/ingest-acl/2026.acl-1.5/",
    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."
}