Continual Learning for LLMs

LLM: Large Language Model

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

256 papers29 papers in the last four weeks, down 37% on the four weeks before. 0.2% of all new papers.

  1. Position: Agentic Evolution is the Path to Evolving LLMs

    Jan 30, 2026Minhua Lin, Hanqing Lu, Zhan Shi +12Online Language Model AdaptationLanguage Model Self-Improvement

  2. Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning

    Jan 24, 2026Fatema Siddika, Md Anwar Hossen, Tanwi Mallick +1Subspace-Based Continual LearningContinual Learning for LLMs

  3. Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

    Nov 25, 2025Xuyuan Liu, Shengyu Chen, Xinshuai Dong +6Knowledge EditingContinual Learning for LLMs

  4. Parameter Importance-Driven Continual Learning for Foundation Models

    Nov 19, 2025Lingxiang Wang, Hainan Zhang, Zhiming ZhengContinual Learning for LLMsParameter-Efficient Fine-Tuning

  5. Mixtures of SubExperts for Large Language Continual Learning

    Nov 9, 2025Haeyong Kang, Hee Suk Yoon, Dahua Feng +1Continual Learning for LLMsMixture-of-Experts Language Models

  6. Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting

    Oct 21, 2025Howard Chen, Noam Razin, Karthik Narasimhan +1Continual Learning for LLMsRL Post-Training

  7. K-Merge: Online Continual Merging of Adapters for On-device Large Language Models

    Oct 15, 2025Donald Shenaj, Ondrej Bohdal, Taha Ceritli +3Continual Learning for LLMsOn-Device Language Model Inference

  8. LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X

    Oct 15, 2025Shuo Xing, Junyuan Hong, Yifan Wang +5LLM TrainingLLM Reliability

  9. Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training

    Jul 7, 2025Song Lai, Haohan Zhao, Rong Feng +9Continual Learning for LLMsLLM Post-Training

  10. Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models

    Jun 21, 2025Yukun Huang, Sanxing Chen, Jian Pei +2Continual Learning for LLMs

  11. TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree

    Jun 12, 2025Yu-Yang Qian, Yuan-Ze Xu, Zhen-Yu Zhang +2Continual Learning for LLMsLow-Rank Adaptation

  12. Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives

    Jan 9, 2025Anat Kleiman, Gintare Karolina Dziugaite, Jonathan Frankle +2Catastrophic ForgettingContinual Learning for LLMs

  13. Continual Memorization of Factoids in Language Models

    Nov 11, 2024Howard Chen, Jiayi Geng, Adithya Bhaskar +2Continual Learning for LLMsMemorization in Language Models