mlsanityData to 14 Oct 2026

Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking

arXiv 2307.01453 ↗First posted 4 Jul 2023cs.CLcited by 10

On the map: Retrieval-augmented generation → Conversational and speech RAG

Abstract (arXiv)

There has been significant interest in zero and few-shot learning for dialogue state tracking (DST) due to the high cost of collecting and annotating task-oriented dialogues. Recent work has demonstrated that in-context learning requires very little data and zero parameter updates, and even outperforms trained methods in the few-shot setting (Hu et al. 2022). We propose RefPyDST, which advances the state of the art with three advancements to in-context learning for DST. First, we formulate DST as a Python programming task, explicitly modeling language coreference as variable reference in Python. Second, since in-context learning depends highly on the context examples, we propose a method to retrieve a diverse set of relevant examples to improve performance. Finally, we introduce a novel re-weighting method during decoding that takes into account probabilities of competing surface forms, and produces a more accurate dialogue state prediction. We evaluate our approach using MultiWOZ and achieve state-of-the-art multi-domain joint-goal accuracy in zero and few-shot settings.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 34 of its 48 references that are in the map. First posted on arXiv 4 Jul 2023.

Builds on

34 of 48 references.

References · 34

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  5. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  6. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  7. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  8. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  9. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  10. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  11. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  12. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
22 more
  1. 2020A Simple Language Model for Task-Oriented Dialoguecited by 332
  2. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 263
  3. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  4. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  5. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  6. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 139
  7. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  8. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 88
  9. 2022Complementary Explanations for Effective In-Context Learningcited by 71
  10. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  11. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  12. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  13. 2020MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotationcited by 51
  14. 2021Few-Shot Semantic Parsing with Language Models Trained On Codecited by 50
  15. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  16. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  17. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  18. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  19. 2022Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Trackingcited by 21
  20. 2020Improving Limited Labeled Dialogue State Tracking with Self-Supervisioncited by 16
  21. 2022Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialoguecited by 16
  22. 2022DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuningcited by 9

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 6; 2025: 3.

10 papers.

  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2024Large Language Models Meet NLP: A Surveycited by 103
  3. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 71
  4. 2024BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicinecited by 31
  5. 2023Supervised Knowledge Makes Large Language Models Better In-context Learnerscited by 20
  6. 2024Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Trackingcited by 6
  7. 2025Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactionscited by 2
  8. 2025When More Retrieval Hurts: Retrieval-Augmented Code Review Generationcited by 2
  9. 2024Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbotcited by 0
  10. 2025Beyond More Context: Retrieval Diversity Boosts Multi-Turn Intent Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking
  2. 2024Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT
  3. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking
  4. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
  5. 2024Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents
  6. 2024A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4
  7. 2026Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
  8. 2026ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue