mlsanityData to 7 Oct 2026

Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel

arXiv 2404.15219 ↗First posted 23 Apr 2024cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e.g. a dialogue state and the system actions taken at each step. These annotations can be costly to produce, error-prone, and require both domain and annotation expertise. With advances in LLMs, we hypothesize that unlabeled data and a schema definition are sufficient for building a working task-oriented dialogue system, completely unsupervised. We consider a novel unsupervised setting of only (1) a well-defined API schema (2) a set of unlabeled dialogues between a user and agent. We propose an innovative approach using expectation-maximization (EM) that infers turn-level annotations as latent variables using a noisy channel model to build an end-to-end dialogue agent. Evaluating our approach on the MultiWOZ benchmark, our method more than doubles the dialogue success rate of a strong GPT-3.5 baseline.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 23 Apr 2024.

Builds on

22 of 31 references.

References · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  6. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  7. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  8. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
  9. 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 163
  10. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  11. 2023Task Contamination: Language Models May Not Be Few-Shot Anymorecited by 98
  12. 2023Are LLMs All You Need for Task-Oriented Dialogue?cited by 52
10 more
  1. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  2. 2020A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learningcited by 47
  3. 2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
  4. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
  5. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  6. 2021Pretraining the Noisy Channel Model for Task-Oriented Dialoguecited by 23
  7. 2018Explicit State Tracking with Semi-Supervision for Neural Dialogue Generationcited by 17
  8. 2021Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systemscited by 13
  9. 2019Towards Universal Dialogue Act Tagging for Task-Oriented Dialoguescited by 7
  10. 2022Learning Interpretable Latent Dialogue Actions With Less Supervisioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Modelcited by 20
  2. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  3. 2025RECAP: REwriting Conversations for Intent Understanding in Agentic Planningcited by 7
  4. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answeringcited by 1
  5. 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challengescited by 0