mlsanityData to 14 Oct 2026

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

arXiv 1804.06512 ↗First posted 18 Apr 2018cs.CLcited by 53

Not on the map. Why?

Abstract (arXiv)

In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction with users by learning from human teaching and feedback. We design a neural network based task-oriented dialogue agent that can be optimized end-to-end with the proposed learning method. Experimental results show that our end-to-end dialogue agent can learn effectively from the mistake it makes via imitation learning from user teaching. Applying reinforcement learning with user feedback after the imitation learning stage further improves the agent's capability in successfully completing a task.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 10; 2022: 10; 2023: 14; 2024: 9; 2025: 7; 2026: 1.

53 papers.

Sort:

By area:

  1. 2019Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialogcited by 284
  2. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  3. 2023DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedbackcited by 103
  4. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  5. 2020Human-centric Dialog Training via Offline Reinforcement Learningcited by 93
  6. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 90
  7. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 87
  8. 2023Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planningcited by 61
  9. 2023Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generationcited by 55
  10. 2023The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Valuescited by 54
  11. 2021Putting Humans in the Natural Language Processing Loop: A Surveycited by 40
  12. 2022CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learningcited by 34
38 more
  1. 2024Planning Like Human: A Dual-process Framework for Dialogue Planningcited by 32
  2. 2021TIAGE: A Benchmark for Topic-Shift Aware Dialog Modelingcited by 22
  3. 2022Context-Aware Language Modeling for Goal-Oriented Dialogue Systemscited by 22
  4. 2022Continual Learning for Instruction Following from Realtime Feedbackcited by 22
  5. 2021Continual Learning for Grounded Instruction Generation by Observing Human Following Behaviorcited by 19
  6. 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 17
  7. 2022Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policycited by 17
  8. 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directionscited by 17
  9. 2022Multimodal Conversational AI: A Survey of Datasets and Approachescited by 16
  10. 2022KETOD: Knowledge-Enriched Task-Oriented Dialoguecited by 12
  11. 2024Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systemscited by 11
  12. 2024Preemptive Detection and Correction of Misaligned Actions in LLM Agentscited by 10
  13. 2022Toward Self-learning End-to-End Task-Oriented Dialog Systemscited by 9
  14. 2023Dealing with Semantic Underspecification in Multimodal NLPcited by 9
  15. 2022Dynamic Planning in Open-Ended Dialogue using Reinforcement Learningcited by 8
  16. 2023Multi-Granularity Prompts for Topic Shift Detection in Dialoguecited by 6
  17. 2023SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language Feedbackcited by 6
  18. 2024Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and Adaptabilitycited by 6
  19. 2021NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedbackcited by 5
  20. 2022Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learningcited by 5
  21. 2024Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challengescited by 5
  22. 2025The Thin Line Between Comprehension and Persuasion in LLMscited by 5
  23. 2021Affective Decoding for Empathetic Response Generationcited by 4
  24. 2023Topic Shift Detection in Chinese Dialogues: Corpus and Benchmarkcited by 4
  25. 2023A Brief History of Prompt: Leveraging Language Models. (Through Advanced Prompting)cited by 4
  26. 2023Prompt Backdoors in Visual Prompt Learningcited by 4
  27. 2025How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyondcited by 4
  28. 2025Spoken Conversational Agents with Large Language Modelscited by 4
  29. 2024MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLUcited by 2
  30. 2025Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Modelscited by 2
  31. 2025Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decompositioncited by 2
  32. 2021Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog Systemcited by 1
  33. 2022Reinforced Approximate Exploratory Data Analysiscited by 1
  34. 2024Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedbackcited by 1
  35. 2025SIL: Symbiotic Interactive Learning for Language-Conditioned Human-Agent Co-Adaptationcited by 1
  36. 2026Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mindcited by 1
  37. 2021AutoNLU: Detecting, root-causing, and fixing NLU model errorscited by 0
  38. 2021Topic-time Heatmaps for Human-in-the-loop Topic Detection and Trackingcited by 0

50 most cited of 53 All 53 (JSON)