Continual Learning for LLMs

LLM: Large Language Model

Ask about this topic

Overview

The field investigates how large language models can keep learning through continual pretraining, instruction tuning, alignment, and personalization without losing earlier knowledge or skills. Common approaches include replaying old or generated examples, distillation and regularization, selective or orthogonal parameter updates, modular adapters, and external memories that leave the model weights unchanged. Evaluations use sequential task suites such as TRACE and SuperNI, domain streams such as biomedical NLP, and evolving knowledge or user-interaction settings, measuring both new-task performance and retention over time. No single approach works reliably across settings: results depend on task order, model capacity, and update type, while long-term evaluation must balance adaptation, forgetting, transfer, safety, and compute cost.

Latest papers

CardsList

236 papers44 papers in the last four weeks, up 110% on the four weeks before. 0.3% of all new papers.

  1. Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts

    Apr 20, 2026Jacob Morrison, Sanjay Adhikesaven, Akshita Bhagia +3Continual Learning for LLMsMixture-of-Experts Language Models

    University of Washington · Allen Institute for AI · University of California, Berkeley

  2. HiP-LoRA: Budgeted Spectral Plasticity for Robust Low-Rank Adaptation

    Apr 20, 2026Lixian Chen, Jianhong TanContinual Learning for LLMsLow-Rank Adaptation

    Guangdong University of Technology

  3. SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models

    Apr 20, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuContinual Learning for LLMsLLM Fine-Tuning

    The University of Hong Kong, Hong Kong, China · Brain Investing Limited, Hong Kong, China

  4. Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning

    Apr 19, 2026Ziqing Zhuang, Linhai Zhang, Jiasheng Si +2Continual Learning for LLMsMeta-Learning

    Southeast University · King’s College London · Qilu University of Technology (Shandong Academy of Sciences) +1

  5. Continual Safety Alignment via Gradient-Based Sample Selection

    Apr 19, 2026Thong Bach, Dung Nguyen, Thao Minh Le +1Continual Learning for LLMsLLM Fine-Tuning

    Applied Artificial Intelligence Initiative (A2I2), Deakin University · Pennsylvania State University

  6. Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization

    Apr 18, 2026Weijie Wan, Jiangjiang ZhaoContinual Learning for LLMsLLM Fine-Tuning

    Shortest Path Technology · China Mobile Communications Group Co.,Ltd

  7. JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models

    Apr 17, 2026Alexandra Dragomir, Ioana Pintilie, Antonio Barbalau +6Continual Learning for LLMsLow-Rank Adaptation

    Bitdefender · ETH Zurich · University of Bucharest

  8. Why Fine-Tuning Encourages Hallucinations and How to Fix It

    Apr 16, 2026Guy Kaplan, Zorik Gekhman, Zhen Zhu +5Supervised Fine-TuningContinual Learning for LLMs

    ♡Hebrew University of Jerusalem · ♣Technion – Israel Institute of Technology · ♢University of Illinois Urbana-Champaign +1

  9. Discovering Novel LLM Experts via Task-Capability Coevolution

    Apr 16, 2026Andrew Dai, Boris Meinardus, Ciaran Regan +2Continual Learning for LLMs

    Sakana AI

  10. Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning

    Apr 15, 2026Zekai Lin, Chao Xue, Di Liang +8Supervised Fine-TuningSelective Fine-Tuning

    Tencent Hunyuan · University of New South Wales · Tencent Yuanbao +2

  11. HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning

    Apr 13, 2026Yangfan Wang, Tianyang Sun, Chen Tang +3Model EditingLanguage Model Editing

    Harbin Institute of Technology · AI Research Center, Midea Group (Shanghai) Co., Ltd. · State Key Laboratory of Smart Farm Technologies and Systems +1

  12. In-Place Test-Time Training

    Apr 7, 2026Guhao Feng, Shengjie Luo, Kai Hua +4Test-Time TrainingContinual Learning for LLMs

    ByteDance Seed · Peking University

  13. Improving Sparse Memory Finetuning

    Apr 6, 2026Satyam Goyal, Anirudh Kanchi, Garv Shah +1Continual Learning for LLMsSparse Fine-Tuning

    University of Michigan, Ann Arbor

  14. RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World

    Apr 6, 2026Hanbing Liu, Lang Cao, Yang LiRetrieval-Augmented GenerationContinual Learning for LLMs

    Tsinghua University; Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University · University of Illinois Urbana-Champaign · School of Artificial Intelligence, Chinese University of Hong Kong (Shenzhen)

  15. GAIN: Multiplicative Modulation for Domain Adaptation

    Apr 6, 2026Hengshuai Yao, Xing Chen, Ahmed Murtadha +1Domain Adaptation for LLMsContinual Learning for LLMs

    Sapient Intelligence · Department of Computing Science, University of Alberta

  16. Autolearn: Learn by Surprise, Commit by Proof

    Apr 2, 2026Kang-Sin ChoiOnline Language Model AdaptationKnowledge Augmentation for Language Models

    Ewha Womans University

  17. Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning

    Apr 1, 2026Mohammad R. Abu AyyashContinual Learning for LLMsLLM Fine-Tuning

    Brains Build Research, Ramallah, Palestine

  18. Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes

    Mar 29, 2026Ashish PandeyCatastrophic ForgettingLow-Rank Adaptation

  19. MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis

    Mar 24, 2026Wei Sun, Ting Wang, Xinran Tian +4Fault DiagnosisContinual Learning for LLMs

    School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen; Shenzhen Future Network of Intelligence Institute, Shenzhen, China · Shenzhen Future Network of Intelligence Institute, Shenzhen, China · China Mobile Communications Group Guangdong Co., Ltd., Guangzhou, China

  20. SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation

    Mar 23, 2026Nitin Vetcha, Dianbo LiuContinual Learning for LLM AgentsContinual Learning for LLMs

    Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore · Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, India

  21. Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training

    Mar 17, 2026Elnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati +2LLM TrainingContinual Learning for LLMs

    University of Southern California

  22. Online Experiential Learning for Language Models

    Mar 17, 2026Tianzhu Ye, Li Dong, Qingxiu Dong +3Continual Learning for LLMsLanguage Model Self-Improvement

    Microsoft Research

  23. MedCL-Bench: Benchmarking stability-efficiency trade-offs and scaling in biomedical continual learning

    Mar 17, 2026Min Zeng, Shuang Zhou, Zaifu Zhan +1Continual LearningContinual Learning for LLMs

    Division of Computational Health Sciences, Department of Surgery, University of Minnesota, Minneapolis, 55455, MN, USA.

  24. Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods

    Mar 17, 2026Hong JeongPersistent Memory for Language ModelsMemory-Augmented Language Models

    Inha University in Tashkent, Uzbekistan

  25. SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing

    Mar 16, 2026Yuhuan Liu, Haitian Zhong, Xinyuan Xia +3Knowledge EditingLanguage Model Editing

    New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences · Cuiying Honors College, Lanzhou University · Zhongguancun Academy +1

  26. Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages

    Mar 13, 2026Hongyang Chen, Zhongwu Sun, Hongfei Ye +2Continual Learning for LLMsCatastrophic Forgetting

    Zhejiang Lab, Hangzhou 311100, China

  27. From Gradients to Riccati Geometry: Kalman World Models for Single-Pass Learning

    Mar 13, 2026Andrew KirulutaGradient-Free OptimizationState Space Models

    UC Berkeley School of Information

  28. NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation

    Mar 12, 2026Yuxin Yang, Haoran Zhang, Mingxuan Li +6Parameter-Efficient Fine-TuningLow-Rank Adaptation

    Shanghai University · Fudan University

  29. Reversible Lifelong Model Editing via Semantic Routing-Based LoRA

    Mar 11, 2026Haihua Luo, Xuming Ran, Tommi Kärkkäinen +4Model EditingLanguage Model Editing

    Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland · National University of Singapore, Singapore · School of Computer Science and Technology, Dalian University of Technology, Dalian, China

  30. MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning

    Mar 10, 2026Yiyang Lu, Yu He, Jianlong Chen +1Continual Learning for LLMsReplay-Based Continual Learning

    The Chinese University of Hong Kong, Shenzhen · Nanjing University