mlsanityData to 7 Oct 2026

Episodic Memory in Lifelong Language Learning

arXiv 1906.01076 ↗First posted 3 Jun 2019cs.LG cs.CL stat.MLcited by 188

Not on the map. Why?

Abstract (arXiv)

We introduce a lifelong language learning setup where a model needs to learn from a stream of text examples without any dataset identifier. We propose an episodic memory model that performs sparse experience replay and local adaptation to mitigate catastrophic forgetting in this setup. Experiments on text classification and question answering demonstrate the complementary benefits of sparse experience replay and local adaptation to allow the model to continuously learn from new datasets. We also show that the space complexity of the episodic memory module can be reduced significantly (~50-90%) by randomly choosing which examples to store in memory with a minimal decrease in performance. We consider an episodic memory component as a crucial building block of general linguistic intelligence and see our model as a first step in that direction.

Key facts. Cited by 188 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 39; 2023: 41; 2024: 38; 2025: 23; 2026: 17.

188 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  3. 2023Orthogonal Subspace Learning for Language Model Continual Learningcited by 296
  4. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 226
  5. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 196
  6. 2023Progressive Prompts: Continual Learning for Language Modelscited by 195
  7. 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 174
  8. 2021Towards Continual Knowledge Learning of Language Modelscited by 172
  9. 2022A Review on Language Models as Knowledge Basescited by 156
  10. 2022Fine-tuned Language Models are Continual Learnerscited by 152
  11. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  12. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
38 more
  1. 2021DEMix Layers: Disentangling Domains for Modular Language Modelingcited by 130
  2. 2021Lifelong Pretraining: Continually Adapting Language Models to Emerging Corporacited by 114
  3. 2024Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsalcited by 114
  4. 2022Training Language Models with Memory Augmentationcited by 112
  5. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  6. 2021LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5cited by 103
  7. 2021Time Waits for No One! Analysis and Challenges of Temporal Misalignmentcited by 91
  8. 2021Continual Learning for Text Classification with Information Disentanglement Based Regularizationcited by 86
  9. 2021Adaptive Semiparametric Language Modelscited by 83
  10. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  11. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  12. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
  13. 2022ELLE: Efficient Lifelong Pre-training for Emerging Datacited by 70
  14. 2023Lifelong Language Pretraining with Distribution-Specialized Expertscited by 64
  15. 2023TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Modelscited by 59
  16. 2023Lawyer LLaMA Technical Reportcited by 54
  17. 2024InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructionscited by 54
  18. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  19. 2022Memory Efficient Continual Learning with Transformerscited by 43
  20. 2021DualNet: Continual Learning, Fast and Slowcited by 39
  21. 2024SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Modelscited by 37
  22. 2021Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learningcited by 35
  23. 2022DSI++: Updating Transformer Memory with New Documentscited by 35
  24. 2021Curriculum-Meta Learning for Order-Robust Continual Relation Extractioncited by 34
  25. 2025SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuningcited by 32
  26. 2022Consistent Representation Learning for Continual Relation Extractioncited by 28
  27. 2024Scalable Language Model with Generalized Continual Learningcited by 28
  28. 2021Continual Learning on Noisy Data Streams via Self-Purified Replaycited by 27
  29. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  30. 2023Dissociating language and thought in large language modelscited by 27
  31. 2023Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learningcited by 27
  32. 2022ConTinTin: Continual Learning from Task Instructionscited by 26
  33. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  34. 2024Rehearsal-Free Modular and Compositional Continual Learning for Language Modelscited by 26
  35. 2022Relational Memory Augmented Language Modelscited by 24
  36. 2022Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Modelscited by 24
  37. 2023Dealing with Cross-Task Class Discrimination in Online Continual Learningcited by 24
  38. 2022Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detectioncited by 23

50 most cited of 188 All 188 (JSON)