Large Language Models (LLMs) have achieved remarkable success across various tasks, yet their ability to learn incrementally without forgetting remains underexplored. Incremental learning (IL) is crucial as it enables models to acquire new knowledge while retaining previously learned information, akin to human learning. Existing benchmarks for IL are insufficient due to data leakage issues and the overqualification of LLMs. To address these challenges, we introduce Concept-1K, a novel dataset comprising 1,023 recently emerged concepts across diverse domains. The concepts in Concept-1K are discrete, interpretable units of knowledge that allow for fine-grained analysis of learning and forgetting processes. Using Concept-1K as a testbed, we aim to answer the question: ``Can LLMs learn new concepts incrementally without forgetting like humans?'' Our investigation reveals that LLMs still suffer from catastrophic forgetting and that LoRA, despite fine-tuning fewer parameters, may lead to more forgetting on training data. Additionally, we explore the roles of in-context learning, model scale, buffer size, and pretraining in IL performance. These findings highlight the strengths and limitations of LLMs in IL scenarios and provide a robust benchmark for future research.
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Pattern Recognition Center, WeChat AI, Tencent Inc(腾讯公司微信AI模式识别中心);School of Engineering, Westlake University(西湖大学工程学院);Institute of Advanced Technology, Westlake Institute for Advanced Study(西湖高等研究院先进技术研究所)
More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);Tongyi Lab, Alibaba Group(阿里巴巴集团通义实验室);Polytechnic Institute, Zhejiang University(浙江大学理工学院)
Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
Department of Computer Science, UCL Centre for Artificial Intelligence, University College London, London, UK(计算机科学系,UCL人工智能中心,伦敦大学学院,伦敦,英国);University of Southampton, Southampton, UK(南安普顿大学,南安普顿,英国)
Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
College of Information Sciences and Technology, Pennsylvania State University(宾夕法尼亚州立大学信息科学与技术学院);School of Computer Science and Technology, Singapore Management University(新加坡管理大学计算机科学与技术学院);School of Computer Science, Hefei Univeristy of Technology(合肥工业大学计算机学院)
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization
Graduate School of AI, KAIST(韩国科学技术院人工智能研究生院);Samsung Advanced Institute of Technology(三星先进技术研究院);Department of Electrical and Computer Engineering, UBC(不列颠哥伦比亚大学电气与计算机工程系)
Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Sun Yat-Sen University(中山大学);Shenzhen MSU-BIT University(深圳北理莫斯科大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))
Countering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model Merging
University of Florida(佛罗里达大学);Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida(佛罗里达大学医学院健康结果与生物医学信息学系);Department of Engineering Education, Herbert Wertheim College of Engineering, University of Florida(佛罗里达大学赫伯特·韦特海姆工程学院工程教育系);Preston A. Wells, Jr. Center for Brain Tumor Therapy, Lillian S. Wells Department of Neurosurgery, University of Florida(佛罗里达大学莉莉安·S·威尔斯神经外科系普雷斯顿·A·威尔斯脑肿瘤治疗中心)
Learning Incrementally to Segment Multiple Organs in a CT Image
The First Affiliated Hospital of Anhui Medical University(安徽医科大学第一附属医院);Huawei Cloud Computing Technology Co. Ltd(华为云计算技术有限公司);University of Science and Technology of China(中国科学技术大学)
Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting
Concordia University(康考迪亚大学);Mila – Quebec AI Institute(米拉-魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);Laval University(拉瓦尔大学);University of Tübingen(蒂宾根大学);Tübingen AI Center(蒂宾根人工智能中心)
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
The Hong Kong Polytechnic University(香港理工大学);ShineMo Ltd., China(中国 ShineMo 公司);Solar System of OVB, Tencent, China(腾讯 OVB 太阳系中国);Peking University(北京大学);University College London(伦敦大学学院);University of Illinois Chicago(伊利诺伊大学芝加哥分校)
Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs
TensorOpera Inc.(TensorOpera公司);Stevens Institute of Technology(史蒂文斯理工学院);University of California, Irvine(加州大学欧文分校);Hong Kong University of Science and Technology(香港科技大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
The Hong Kong Polytechnic University(香港理工大学);Carnegie Mellon University(卡内基梅隆大学);University of California, Santa Cruz(加州大学圣克ruz分校);Huawei Technologies(华为技术有限公司);Research Centre for Privacy and Security Technologies in Future Smart Systems, PolyU(未来智能系统中的隐私与安全技术研究中心,PolyU)
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Peng Cheng Laboratory(鹏城实验室);Huazhong University of Science and Technology(华中科技大学);Xiamen University(厦门大学);The Hong Kong University of Science and Technology, Guangzhou(香港科技大学(广州));School of Biomedical Engineering, Tsinghua University(清华大学生物医学工程学院)
Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
School of Informatics, Xiamen University(厦门大学信息学院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Tencent AI Lab(腾讯AI实验室);Zhejiang University(浙江大学)