mlsanityData to 7 Oct 2026

In-Context Learning for Few-Shot Dialogue State Tracking

arXiv 2203.08568 ↗First posted 16 Mar 2022cs.CLcited by 47

Not on the map. Why?

Abstract (arXiv)

Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we propose an in-context learning (ICL) framework for zero-shot and few-shot learning DST, where a large pre-trained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates. To better leverage a tabular domain description in the LM prompt, we reformulate DST into a text-to-SQL problem. We also propose a novel approach to retrieve annotated dialogues as exemplars. Empirical results on MultiWOZ show that our method IC-DST substantially outperforms previous fine-tuned state-of-the-art models in few-shot settings. In addition, we test IC-DST in zero-shot settings, in which the model only takes a fixed task instruction as input, finding that it outperforms previous zero-shot methods by a large margin.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 43 of its 74 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

43 of 74 references.

References · 43

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  6. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  7. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  8. 2021MetaICL: Learning to Learn In Contextcited by 450
  9. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  10. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  11. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  12. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 209
31 more
  1. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  2. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  3. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  4. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  5. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
  6. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  7. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  8. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  9. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  10. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
  11. 2020DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialoguecited by 89
  12. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 86
  13. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  14. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  15. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
  16. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  17. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  18. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  19. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  20. 2021Few-Shot Semantic Parsing with Language Models Trained On Codecited by 50
  21. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  22. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  23. 2020Conversational Semantic Parsing for Dialog State Trackingcited by 40
  24. 2019BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformercited by 37
  25. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  26. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  27. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  28. 2021DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualizationcited by 21
  29. 2022Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Trackingcited by 21
  30. 2020Improving Limited Labeled Dialogue State Tracking with Self-Supervisioncited by 16
  31. 2021Contextual Semantic Parsing for Multilingual Task-Oriented Dialoguescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 20; 2024: 11; 2025: 6; 2026: 3.

47 papers.

Sort:

By area:

  1. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
  2. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 389
  3. 2022Binding Language Models in Symbolic Languagescited by 224
  4. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  5. 2022PromptCap: Prompt-Guided Task-Aware Image Captioningcited by 104
  6. 2024Large Language Models Meet NLP: A Surveycited by 102
  7. 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 94
  8. 2023Divide & Bind Your Attention for Improved Generative Semantic Nursingcited by 80
  9. 2023Lemur: Harmonizing Natural Language and Code for Language Agentscited by 71
  10. 2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 69
  11. 2023Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Modelscited by 66
  12. 2023LayoutPrompter: Awaken the Design Ability of Large Language Modelscited by 47
35 more
  1. 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46
  2. 2022Controllable Dialogue Simulation with In-Context Learningcited by 42
  3. 2023MoT: Memory-of-Thought Enables ChatGPT to Self-Improvecited by 37
  4. 2023Can Whisper perform speech-based in-context learning?cited by 35
  5. 2022Workflow Discovery from Dialogues in the Low Data Regimecited by 12
  6. 2024VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesiscited by 11
  7. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  8. 2024STAND-Guard: A Small Task-Adaptive Content Moderation Modelcited by 11
  9. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  10. 2023Diverse Retrieval-Augmented In-Context Learning for Dialogue State Trackingcited by 10
  11. 2023MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluationcited by 10
  12. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  13. 2022Mediators: Conversational Agents Explaining NLP Model Behaviorcited by 7
  14. 2023Submodular Minimax Optimization: Finding Effective Setscited by 7
  15. 2023GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottleneckscited by 6
  16. 2023Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsingcited by 5
  17. 2023Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Trackingcited by 5
  18. 2024Are Human Conversations Special? A Large Language Model Perspectivecited by 5
  19. 2026Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptationcited by 4
  20. 2022MetaASSIST: Robust Dialogue State Tracking with Meta Learningcited by 3
  21. 2023Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schemacited by 3
  22. 2022Leveraging Natural Supervision for Language Representation Learning and Generationcited by 2
  23. 2024Efficient Encoder-Decoder Transformer Decoding for Decomposable Taskscited by 2
  24. 2023Building blocks for complex tasks: Robust generative event extraction for radiology reports under domain shiftscited by 1
  25. 2023Injecting linguistic knowledge into BERT for Dialogue State Trackingcited by 0
  26. 2024State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Trackingcited by 0
  27. 2024Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Expertscited by 0
  28. 2024Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbotcited by 0
  29. 2025Factors affecting the in-context learning abilities of LLMs for dialogue state trackingcited by 0
  30. 2025Hybrid Dialogue State Tracking for Persian Chatbots: A Language Model-Based Approachcited by 0
  31. 2025Beyond More Context: Retrieval Diversity Boosts Multi-Turn Intent Understandingcited by 0
  32. 2025In-Context-Learning-Assisted Quality Assessment Vision-Language Models for Metal Additive Manufacturingcited by 0
  33. 2025MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversationscited by 0
  34. 2026Conversation as Measurement in Clinical Encounters: Observable Phase Structure, Partially Observable Patient Statecited by 0
  35. 2026Lost with a Map: Conversational State and Behavioral Reliability in Language Modelscited by 0