mlsanityData to 14 Oct 2026

ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?

arXiv 2306.01386 ↗First posted 2 Jun 2023cs.CL cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

Recent research on dialogue state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas. However, performance gains heavily depend on aggressive data augmentation and fine-tuning of ever larger language model based architectures. In contrast, general purpose language models, trained on large amounts of diverse data, hold the promise of solving any kind of task without task-specific training. We present preliminary experimental results on the ChatGPT research preview, showing that ChatGPT achieves state-of-the-art performance in zero-shot DST. Despite our findings, we argue that properties inherent to general purpose models limit their ability to replace specialized systems. We further theorize that the in-context learning capabilities of such models will likely become powerful tools to support the development of dedicated and dynamic dialogue state trackers.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 26 of its 46 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

26 of 46 references.

References · 26

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2017Deep reinforcement learning from human preferencescited by 3,912
  5. 2020Learning to summarize from human feedbackcited by 2,588
  6. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  8. 2022Improving alignment of dialogue agents via targeted human judgementscited by 531
  9. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  10. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  11. 2016Neural Belief Tracker: Data-Driven Dialogue State Trackingcited by 143
  12. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
14 more
  1. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  2. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  3. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  4. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  5. 2020Overview of the Ninth Dialog System Technology Challenge: DSTC9cited by 49
  6. 2018Global-Locally Self-Attentive Dialogue State Trackercited by 45
  7. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  8. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  9. 2020Schema-Guided Dialogue State Tracking Task at DSTC8cited by 32
  10. 2021Slot Self-Attentive Dialogue State Trackingcited by 27
  11. 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
  12. 2017An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialogcited by 17
  13. 2022Robust Dialogue State Tracking with Weak Supervision and Sparse Datacited by 15
  14. 2022Dynamic Dialogue Policy for Continual Reinforcement Learningcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 19; 2025: 8; 2026: 2.

38 papers.

Sort:

By area:

  1. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 229
  2. 2024Large Language Models Meet NLP: A Surveycited by 103
  3. 2024A Full-duplex Speech Dialogue Scheme Based On Large Language Modelscited by 40
  4. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  5. 2024Can Large Language Models Understand Context?cited by 26
  6. 2023Towards LLM-driven Dialogue State Trackingcited by 25
  7. 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directionscited by 17
  8. 2024SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Trackingcited by 17
  9. 2024DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Modelscited by 15
  10. 2023Affect Recognition in Conversations Using Large Language Modelscited by 9
  11. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  12. 2024Task-Oriented Dialogue with In-Context Learningcited by 8
26 more
  1. 2024Continual Dialogue State Tracking via Reason-of-Select Distillationcited by 8
  2. 2023S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMscited by 7
  3. 2024Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Trackingcited by 6
  4. 2025The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogscited by 6
  5. 2023Self-Explanation Prompting Improves Dialogue Understanding in Large Language Modelscited by 5
  6. 2023Interpreting User Requests in the Context of Natural Language Standing Instructionscited by 5
  7. 2024Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channelcited by 5
  8. 2023A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systemscited by 4
  9. 2023Speech-based Slot Filling using Large Language Modelscited by 3
  10. 2024Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPTcited by 3
  11. 2024A Career Interview Dialogue System using Large Language Model-based Dynamic Slot Generationcited by 3
  12. 2025LANID: LLM-assisted New Intent Discoverycited by 3
  13. 2023A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correctioncited by 2
  14. 2024Plan, Generate and Complicate: Improving Low-resource Dialogue State Tracking via Easy-to-Difficult Zero-shot Data Augmentationcited by 2
  15. 2024A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understandingcited by 2
  16. 2025All Learning Has an Emotional Basis, So Does Task-Oriented Dialoguecited by 2
  17. 2024DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Modelscited by 1
  18. 2024MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Trackingcited by 1
  19. 2024Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Trackingcited by 1
  20. 2025Enhancing the Preference Extractor in Multi-turn Dialogues: From Annotating Disasters to Accurate Preference Extractioncited by 1
  21. 2025PyTOD: Programmable Task-Oriented Dialogue with Execution Feedbackcited by 1
  22. 2025NOEM3A: a Neuro-symbolic Ontology-Enhanced Method for Multi-intent understanding in Mobile Agentscited by 1
  23. 2024A Survey on the Real Power of ChatGPTcited by 0
  24. 2025HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DSTcited by 0
  25. 2026Conversation as Measurement in Clinical Encounters: Observable Phase Structure, Partially Observable Patient Statecited by 0
  26. 2026Lost with a Map: Conversational State and Behavioral Reliability in Language Modelscited by 0