mlsanityData to 7 Oct 2026

A Simple Language Model for Task-Oriented Dialogue

arXiv 2005.00796 ↗First posted 2 May 2020cs.CLcited by 331

Not on the map. Why?

Abstract (arXiv)

Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified approach leads to state-of-the-art performance on the MultiWOZ dataset. SimpleTOD is a simple approach to task-oriented dialogue that uses a single, causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2. SimpleTOD improves over the prior state-of-the-art in joint goal accuracy for dialogue state tracking, and our analysis reveals robustness to noisy annotations in this setting. SimpleTOD also improves the main metrics used to evaluate action decisions and response generation in an end-to-end setting: inform rate by 8.1 points, success rate by 9.7 points, and combined score by 7.2 points.

Key facts. Cited by 331 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 77; 2022: 96; 2023: 78; 2024: 40; 2025: 19; 2026: 21.

331 papers.

Sort:

By area:

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  3. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  4. 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 264
  5. 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 245
  6. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  7. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  8. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  9. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  10. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  11. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  12. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
38 more
  1. 2021Truthful AI: Developing and governing AI that does not liecited by 109
  2. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  3. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
  4. 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 94
  5. 2021Language Models are Few-shot Multilingual Learnerscited by 92
  6. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 86
  7. 2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 86
  8. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  9. 2021Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systemscited by 73
  10. 2023A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospectscited by 66
  11. 2022DialFRED: Dialogue-Enabled Agents for Embodied Instruction Followingcited by 63
  12. 2022Keep Me Updated! Memory Management in Long-term Conversationscited by 62
  13. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  14. 2021BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modelingcited by 55
  15. 2021SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversationscited by 54
  16. 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generationcited by 54
  17. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  18. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  19. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  20. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  21. 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
  22. 2022Continual Prompt Tuning for Dialog State Trackingcited by 44
  23. 2022Controllable Dialogue Simulation with In-Context Learningcited by 42
  24. 2022Neural Approaches to Conversational Information Retrievalcited by 41
  25. 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
  26. 2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
  27. 2021Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Trackingcited by 35
  28. 2021Transferable Dialogue Systems and User Simulatorscited by 35
  29. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  30. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  31. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  32. 2022CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learningcited by 33
  33. 2024SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generationcited by 33
  34. 2021Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representationcited by 32
  35. 2022A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systemscited by 32
  36. 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
  37. 2021Semi-Supervised Variational Reasoning for Medical Dialogue Generationcited by 30
  38. 2021Annotation Inconsistency and Entity Bias in MultiWOZcited by 30

50 most cited of 331 All 331 (JSON)