mlsanityData to 7 Oct 2026

Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue

arXiv 2210.07783 ↗First posted 14 Oct 2022cs.CL cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems. To address the catastrophic forgetting issue of LL, generative replay methods are widely employed to consolidate past knowledge with generated pseudo samples. However, most existing generative replay methods use only a single task-specific token to control their models. This scheme is usually not strong enough to constrain the generative model due to insufficient information involved. In this paper, we propose a novel method, prompt conditioned VAE for lifelong learning (PCLL), to enhance generative replay by incorporating tasks' statistics. PCLL captures task-specific distributions with a conditional variational autoencoder, conditioned on natural language prompts to guide the pseudo-sample generation. Moreover, it leverages a distillation process to further consolidate past knowledge by alleviating the noise in pseudo samples. Experiments on natural language understanding tasks of ToD systems demonstrate that PCLL significantly outperforms competitive baselines in building LL models.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 72 of its 94 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

72 of 94 references.

References · 72

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  7. 2013Auto-Encoding Variational Bayescited by 3,980
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2016Learning without Forgettingcited by 2,465
  10. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  11. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  12. 2019Language Models as Knowledge Bases?cited by 1,922
38 more
  1. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  2. 2016Progressive Neural Networkscited by 1,332
  3. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  4. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  5. 2017Continual Learning with Deep Generative Replaycited by 1,152
  6. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  7. 2018Experience Replay for Continual Learningcited by 1,074
  8. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  9. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  10. 2019How Can We Know What Language Models Know?cited by 953
  11. 2021Learning to Prompt for Continual Learningcited by 938
  12. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  13. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  14. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  15. 2015Generating Sentences from a Continuous Spacecited by 607
  16. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  17. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  18. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
  19. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
  20. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  21. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  22. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
  23. 2018Learning without Memorizingcited by 249
  24. 2021PPT: Pre-trained Prompt Tuning for Few-shot Learningcited by 232
  25. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  26. 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
  27. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  28. 2019Benchmarking Natural Language Understanding Services for building Conversational Agentscited by 166
  29. 2019LAMOL: LAnguage MOdeling for Lifelong Language Learningcited by 156
  30. 2020Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Spacecited by 114
  31. 2021LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5cited by 103
  32. 2017Encoder Based Lifelong Learningcited by 102
  33. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  34. 2018Semantic Parsing for Task Oriented Dialog using Hierarchical Representationscited by 101
  35. 2019Uncertainty-guided Continual Learning with Bayesian Neural Networkscited by 100
  36. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  37. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 86
  38. 2020Continual Learning in Task-Oriented Dialogue Systemscited by 82

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 2; 2025: 2; 2026: 1.

8 papers.

  1. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  2. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  3. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  4. 2023Continual Learning with Dirichlet Generative-based Rehearsalcited by 7
  5. 2025LSEBMCL: A Latent Space Energy-Based Model for Continual Learningcited by 2
  6. 2026MedCL-Bench: Benchmarking stability-efficiency trade-offs and scaling in biomedical continual learningcited by 2
  7. 2022Semi-Supervised Lifelong Language Learningcited by 1
  8. 2025Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approachcited by 0