mlsanityData to 14 Oct 2026

Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue

arXiv 2204.04327 ↗First posted 8 Apr 2022cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Building universal dialogue systems that operate across multiple domains/APIs and generalize to new ones with minimal overhead is a critical challenge. Recent works have leveraged natural language descriptions of schema elements to enable such systems; however, descriptions only indirectly convey schema semantics. In this work, we propose Show, Don't Tell, which prompts seq2seq models with a labeled example dialogue to show the semantics of schema elements rather than tell the model through descriptions. While requiring similar effort from service developers as generating descriptions, we show that using short examples as schema representations with large language models results in state-of-the-art performance on two popular dialogue state tracking benchmarks designed to measure zero-shot generalization - the Schema-Guided Dialogue dataset and the MultiWOZ leave-one-out benchmark.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 8 Apr 2022.

Builds on

27 of 40 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  5. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  6. 2019How Can We Know What Language Models Know?cited by 959
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  8. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
  9. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  10. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  11. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  12. 2021How Many Data Points is a Prompt Worth?cited by 198
15 more
  1. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  2. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
  3. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  4. 2019SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Trackingcited by 63
  5. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  6. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  7. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  8. 2020A Sequence-to-Sequence Approach to Dialogue State Trackingcited by 43
  9. 2020Language Models as Few-Shot Learner for Task-Oriented Dialogue Systemscited by 41
  10. 2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
  11. 2020Schema-Guided Dialogue State Tracking Task at DSTC8cited by 32
  12. 2020MA-DST: Multi-Attention Based Scalable Dialog State Trackingcited by 24
  13. 2019An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classificationcited by 20
  14. 2020Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Trackingcited by 11
  15. 2021SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Servicescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 2; 2025: 1; 2026: 1.

16 papers.

Sort:

By area:

  1. 2024Large Language Models Meet NLP: A Surveycited by 103
  2. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  3. 2024Retrieval Augmented End-to-End Spoken Dialog Modelscited by 20
  4. 2022AnyTOD: A Programmable Task-Oriented Dialog Systemcited by 10
  5. 2023Diverse Retrieval-Augmented In-Context Learning for Dialogue State Trackingcited by 10
  6. 2022DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuningcited by 9
  7. 2023Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understandingcited by 9
  8. 2023Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuningcited by 8
  9. 2022Knowledge-grounded Dialog State Trackingcited by 5
  10. 2023Continual Dialogue State Tracking via Example-Guided Question Answeringcited by 4
  11. 2023Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Rankingcited by 4
  12. 2023Span-Selective Linear Attention Transformers for Effective and Robust Schema-Guided Dialogue State Trackingcited by 2
4 more
  1. 2025Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactionscited by 2
  2. 2023Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turnscited by 1
  3. 2023UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Trackingcited by 1
  4. 2026Show, Don't Tell: Detecting Novel Objects by Watching Human Videoscited by 0