Model fusion research aims to aggregate the knowledge of multiple individual models to enhance performance by combining their weights. In this work, we study the inverse problem: investigating whether model fusion can be used to reduce unwanted knowledge. We investigate the effects of model fusion in three scenarios: the learning of shortcuts, social biases, and memorization of training data in fine-tuned language models. Through experiments covering classification and generation tasks, our analysis highlights that shared knowledge among models is enhanced during model fusion, while unshared knowledge is usually forgotten. Based on this observation, we demonstrate the potential of model fusion as a debiasing tool and showcase its efficacy in addressing privacy concerns associated with language models.
Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models
LMU Munich(慕尼黑大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Mila – Quebec AI Institute(魁北克人工智能研究所);University of Montreal(蒙特利尔大学);Saarland University(萨尔大学)
Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models
Harbin Institute of Technology(哈尔滨工业大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);Unlimidata Ltd(Unlimidata有限公司);The Chinese University of Hong Kong(香港中文大学);University of Calabria(卡拉布里亚大学)
University of Maryland, College Park(马里兰大学帕克分校);Google Research(谷歌研究院)
大型Transformer模型在许多自然语言任务中取得了令人印象深刻的性能。特别地,基于Transformer的语言模型已经被证明在以其大量参数对事实知识进行编码方面具有很强的能力。虽然提高Transformers的记忆和概括能力的任务已经得到了广泛的研究,但如何使transformers忘记特定的旧事实并记住新事实还不太清楚。在本文中,我们提出了一个新的任务\emph{explicitly modifying specific factual knowledge in Transformer models while ensuring the model performance does not degrade on the unmodified facts}。此任务在许多情况下都很有用,例如更新陈旧的知识,保护隐私,以及消除存储在模型中的意外偏见。我们对几种方法进行了基准测试,这些方法在这项任务上提供了自然的基线性能。这导致了Transformer模型的关键组件的发现,这些组件对于知识修改特别有效。这项工作还提供了不同的训练阶段(如预训练和微调)对记忆和知识修改的作用的见解。
Knowledge Fusion of Large Language Models Via Modular SkillPacks
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));The Hong Kong Polytechnic University(香港理工大学);Nanyang Technological University(南洋理工大学);Huazhong University of Science and Technology(华中科技大学)
From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models
College of Computer Science and Artificial Intelligence, Fudan University(复旦大学计算机科学与人工智能学院);Shanghai University of Electric Power(上海电力大学);School of Information Science and Engineering, East China University of Science and Technology(东华大学信息科学与工程学院)