mlsanityData to 7 Oct 2026

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

arXiv 2109.07263 ↗First posted 15 Sep 2021cs.CL cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain-specific flowcharts, which the agent is supposed to follow during the conversation. Our task exposes novel technical challenges for neural TOD, such as grounding an utterance to the flowchart without explicit annotation, referring to additional manual pages when user asks a clarification question, and ability to follow unseen flowcharts at test time. We release a dataset (FloDial) consisting of 2,738 dialogs grounded on 12 different troubleshooting flowcharts. We also design a neural model, FloNet, which uses a retrieval-augmented generation architecture to train the dialog agent. Our experiments find that FloNet can do zero-shot transfer to unseen flowcharts, and sets a strong baseline for future research.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 28 of its 41 references that are in the map. First posted on arXiv 15 Sep 2021.

Builds on

28 of 41 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  8. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  9. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  10. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  11. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  12. 2015A Neural Conversational Modelcited by 195
16 more
  1. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  2. 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 139
  3. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
  4. 2020Knowledge-Grounded Dialogue Generation with Pre-trained Language Modelscited by 107
  5. 2016Learning End-to-End Goal-Oriented Dialogcited by 104
  6. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  7. 2017Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systemscited by 84
  8. 2018Interpretation of Natural Language Rules in Conversational Machine Readingcited by 72
  9. 2018Building a Conversational Agent Overnight with Dialogue Self-Playcited by 70
  10. 2015A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestioncited by 68
  11. 2020Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Accesscited by 58
  12. 2018Zero-Shot Dialog Generation with Cross-Domain Latent Actionscited by 23
  13. 2016Conditional Generation and Snapshot Learning in Neural Dialogue Systemscited by 17
  14. 2018Disentangling Language and Knowledge in Task-Oriented Dialogscited by 17
  15. 2018Multi-level Memory for Task Oriented Dialogscited by 14
  16. 2017Understanding Task Design Trade-offs in Crowdsourced Paraphrase Collectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 5; 2025: 1; 2026: 5.

19 papers.

Sort:

By area:

  1. 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
  2. 2024Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Modelscited by 37
  3. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
  4. 2024Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extractioncited by 8
  5. 2023Conversational Tree Search: A New Hybrid Dialog Taskcited by 7
  6. 2025Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversationscited by 6
  7. 2026On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agentscited by 6
  8. 2023TOD-Flow: Modeling the Structure of Task-Oriented Dialoguescited by 4
  9. 2024Towards a Zero-Data, Controllable, Adaptive Dialog Systemcited by 4
  10. 2023CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogscited by 3
  11. 2022CookDial: A dataset for task-oriented dialogs grounded in procedural documentscited by 2
  12. 2022TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotationcited by 2
7 more
  1. 2022A Major Obstacle for NLP Research: Let's Talk about Time Allocation!cited by 1
  2. 2023Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generationcited by 1
  3. 2024DFlow: Diverse Dialogue Flow Simulation with Large Language Modelscited by 1
  4. 2026Game of Thought: Robust Information Seeking with Large Language Models Using Game Theorycited by 1
  5. 2026Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Frameworkcited by 1
  6. 2026FloCA: Towards Faithful and Logically Consistent Flowchart Reasoningcited by 0
  7. 2026DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialoguecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment
  2. 2022AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog
  3. 2024Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding
  4. 2024Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents
  5. 2021Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
  6. 2025Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents
  7. 2025Improving Multi-turn Task Completion in Task-Oriented Dialog Systems via Prompt Chaining and Fine-Grained Feedback
  8. 2023Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision