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

arXiv: https://arxiv.org/abs/2204.04327 · HTML: https://mlsanity.com/paper/2204.04327/

## 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 (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking](https://mlsanity.com/paper/2005.02877/) (2020)
- [Dialogue State Tracking with a Language Model using Schema-Driven Prompting](https://mlsanity.com/paper/2109.07506/) (2021)
- [Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2005.00891/) (2020)
- [SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking](https://mlsanity.com/paper/1907.07421/) (2019)
- [Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking](https://mlsanity.com/paper/2105.04222/) (2021)
- [Zero-Shot Dialogue State Tracking via Cross-Task Transfer](https://mlsanity.com/paper/2109.04655/) (2021)
- [Description-Driven Task-Oriented Dialog Modeling](https://mlsanity.com/paper/2201.08904/) (2022)
- [A Sequence-to-Sequence Approach to Dialogue State Tracking](https://mlsanity.com/paper/2011.09553/) (2020)
- [Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2008.06239/) (2020)
- [SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems](https://mlsanity.com/paper/2110.06800/) (2021)
- [Schema-Guided Dialogue State Tracking Task at DSTC8](https://mlsanity.com/paper/2002.01359/) (2020)
- [MA-DST: Multi-Attention Based Scalable Dialog State Tracking](https://mlsanity.com/paper/2002.08898/) (2020)
- [An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classification](https://mlsanity.com/paper/1912.09297/) (2019)
- [Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2002.00181/) (2020)
- [SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services](https://mlsanity.com/paper/2105.08049/) (2021)

## Built on by (most cited first, 16 of 16)

- [Large Language Models Meet NLP: A Survey](https://mlsanity.com/paper/2405.12819/) (2024)
- ["Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking](https://mlsanity.com/paper/2207.14627/) (2022)
- [Retrieval Augmented End-to-End Spoken Dialog Models](https://mlsanity.com/paper/2402.01828/) (2024)
- [AnyTOD: A Programmable Task-Oriented Dialog System](https://mlsanity.com/paper/2212.09939/) (2022)
- [Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking](https://mlsanity.com/paper/2307.01453/) (2023)
- [DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning](https://mlsanity.com/paper/2212.02851/) (2022)
- [Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding](https://mlsanity.com/paper/2306.07944/) (2023)
- [Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning](https://mlsanity.com/paper/2301.10915/) (2023)
- [Knowledge-grounded Dialog State Tracking](https://mlsanity.com/paper/2210.06656/) (2022)
- [Continual Dialogue State Tracking via Example-Guided Question Answering](https://mlsanity.com/paper/2305.13721/) (2023)
- [Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking](https://mlsanity.com/paper/2307.14440/) (2023)
- [Span-Selective Linear Attention Transformers for Effective and Robust Schema-Guided Dialogue State Tracking](https://mlsanity.com/paper/2306.09340/) (2023)
- [Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions](https://mlsanity.com/paper/2504.18474/) (2025)
- [Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns](https://mlsanity.com/paper/2309.13448/) (2023)
- [UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2310.10492/) (2023)
- [Show, Don't Tell: Detecting Novel Objects by Watching Human Videos](https://mlsanity.com/paper/2603.12751/) (2026)

## 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.