mlsanityData to 7 Oct 2026

Dialogue State Tracking with a Language Model using Schema-Driven Prompting

arXiv 2109.07506 ↗First posted 15 Sep 2021cs.CLcited by 94

Not on the map. Why?

Abstract (arXiv)

Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures with special-purpose classifiers. Recently, good results have been obtained using more general architectures based on pretrained language models. Here, we introduce a new variation of the language modeling approach that uses schema-driven prompting to provide task-aware history encoding that is used for both categorical and non-categorical slots. We further improve performance by augmenting the prompting with schema descriptions, a naturally occurring source of in-domain knowledge. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: MultiWOZ 2.1 and M2M. The data and code will be available at https://github.com/chiahsuan156/DST-as-Prompting.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 32 of its 41 references that are in the map. First posted on arXiv 15 Sep 2021.

Builds on

32 of 41 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2018Self-Attention with Relative Position Representationscited by 1,112
  7. 2019How Can We Know What Language Models Know?cited by 953
  8. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  9. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  10. 2020Recipes for building an open-domain chatbotcited by 593
  11. 2020Towards a Human-like Open-Domain Chatbotcited by 467
  12. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
20 more
  1. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  2. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  3. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
  4. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
  5. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  6. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  7. 2019ConveRT: Efficient and Accurate Conversational Representations from Transformerscited by 95
  8. 2020Few-shot Natural Language Generation for Task-Oriented Dialogcited by 89
  9. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  10. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  11. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
  12. 2018Building a Conversational Agent Overnight with Dialogue Self-Playcited by 70
  13. 2020A Sequence-to-Sequence Approach to Dialogue State Trackingcited by 43
  14. 2019Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answeringcited by 39
  15. 2019BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformercited by 37
  16. 2019Pretraining Methods for Dialog Context Representation Learningcited by 35
  17. 2020Schema-Guided Dialogue State Tracking Task at DSTC8cited by 32
  18. 2021Slot Self-Attentive Dialogue State Trackingcited by 27
  19. 2017Scalable Multi-Domain Dialogue State Trackingcited by 22
  20. 2018Multi-task learning for Joint Language Understanding and Dialogue State Trackingcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 28; 2023: 35; 2024: 20; 2025: 6; 2026: 4.

94 papers.

Sort:

By area:

  1. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  2. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  3. 2023Towards Learning a Generalist Model for Embodied Navigationcited by 135
  4. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 115
  5. 2022PromptCap: Prompt-Guided Task-Aware Image Captioningcited by 104
  6. 2022I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classificationcited by 54
  7. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  8. 2023Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Datacited by 48
  9. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  10. 2022Continual Prompt Tuning for Dialog State Trackingcited by 44
  11. 2023Statler: State-Maintaining Language Models for Embodied Reasoningcited by 40
  12. 2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
38 more
  1. 2022A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systemscited by 32
  2. 2022Zero-Shot Rumor Detection with Propagation Structure via Prompt Learningcited by 32
  3. 2023Controllable Mixed-Initiative Dialogue Generation through Promptingcited by 32
  4. 2023Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue Systemcited by 30
  5. 2023Towards LLM-driven Dialogue State Trackingcited by 25
  6. 2024Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulationcited by 24
  7. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  8. 2023Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuningcited by 21
  9. 2024MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotationscited by 21
  10. 2023OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Trackingcited by 17
  11. 2024SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Trackingcited by 17
  12. 2022Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialoguecited by 16
  13. 2025MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agentscited by 16
  14. 2023Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineeringcited by 13
  15. 2022A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancementcited by 12
  16. 2022Dynamic Dialogue Policy for Continual Reinforcement Learningcited by 12
  17. 2022Workflow Discovery from Dialogues in the Low Data Regimecited by 12
  18. 2023Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Modelscited by 12
  19. 2025WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wildcited by 11
  20. 2022AnyTOD: A Programmable Task-Oriented Dialog Systemcited by 10
  21. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  22. 2023MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluationcited by 10
  23. 2022DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuningcited by 9
  24. 2024StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Lossescited by 9
  25. 2024DARD: A Multi-Agent Approach for Task-Oriented Dialog Systemscited by 9
  26. 2022A Dual Prompt Learning Framework for Few-Shot Dialogue State Trackingcited by 8
  27. 2023Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuningcited by 8
  28. 2024Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summariescited by 8
  29. 2023Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervisioncited by 7
  30. 2023End-to-end Story Plot Generatorcited by 7
  31. 2024Are LLMs Robust for Spoken Dialogues?cited by 7
  32. 2022Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Trackingcited by 6
  33. 2022Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Modelscited by 6
  34. 2022Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systemscited by 6
  35. 2023Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Trackingcited by 6
  36. 2023PromptAttack: Probing Dialogue State Trackers with Adversarial Promptscited by 6
  37. 2023On the Effectiveness of Offline RL for Dialogue Response Generationcited by 6
  38. 2022Do Prompts Solve NLP Tasks Using Natural Language?cited by 5

50 most cited of 94 All 94 (JSON)