mlsanityData to 7 Oct 2026

TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation

arXiv 2408.09857 ↗First posted 19 Aug 2024cs.CLcited by 18

Not on the map. Why?

Abstract (arXiv)

A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL over existing state-of-the-art methods. The source code is provided for reproducibility.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 19 Aug 2024.

Builds on

23 of 40 references.

References · 23

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  8. 2016Learning without Forgettingcited by 2,465
  9. 2019Are Sixteen Heads Really Better than One?cited by 803
  10. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  11. 2020Movement Pruning: Adaptive Sparsity by Fine-Tuningcited by 398
  12. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
11 more
  1. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  2. 2023Task-Specific Skill Localization in Fine-tuned Language Modelscited by 104
  3. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  4. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  5. 2020Continual Learning in Task-Oriented Dialogue Systemscited by 82
  6. 2022PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importancecited by 79
  7. 2021Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalizationcited by 56
  8. 2023Weighted Ensemble Models Are Strong Continual Learnerscited by 41
  9. 2023Parameter-Level Soft-Masking for Continual Learningcited by 39
  10. 2021Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Maskingcited by 22
  11. 2023Continual Dialogue State Tracking via Example-Guided Question Answeringcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 14; 2026: 4.

18 papers.

Sort:

By area:

  1. 2025HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Modelscited by 17
  2. 2025Recurrent Knowledge Identification and Fusion for Language Model Continual Learningcited by 14
  3. 2025Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Modelscited by 12
  4. 2025LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Modelscited by 11
  5. 2025Continual Learning for Generative AI: From LLMs to MLLMs and Beyondcited by 9
  6. 2025Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMscited by 7
  7. 2026FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learningcited by 7
  8. 2025GeoEdit: Geometric Knowledge Editing for Large Language Modelscited by 6
  9. 2025PostAlign: Multimodal Grounding as a Corrective Lens for MLLMscited by 5
  10. 2025AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learningcited by 4
  11. 2025ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuningcited by 4
  12. 2025DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Searchcited by 2
6 more
  1. 2025LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimizationcited by 1
  2. 2025Enhancing the Preference Extractor in Multi-turn Dialogues: From Annotating Disasters to Accurate Preference Extractioncited by 1
  3. 2025Mixtures of SubExperts for Large Language Continual Learningcited by 0
  4. 2026CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learningcited by 0
  5. 2026Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Modelscited by 0
  6. 2026Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learningcited by 0