Data to 7 Oct 2026

Task-Oriented Dialogue as Dataflow Synthesis

arXiv 2009.11423 ↗First posted 24 Sep 2020cs.CLcited by 122

Not on the map. Why?

Abstract (arXiv)

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people. Experiments show that dataflow graphs and metacomputation substantially improve representability and predictability in these natural dialogues. Additional experiments on the MultiWOZ dataset show that our dataflow representation enables an otherwise off-the-shelf sequence-to-sequence model to match the best existing task-specific state tracking model. The SMCalFlow dataset and code for replicating experiments are available at https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines.

Key facts. Cited by 122 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 40; 2023: 30; 2024: 14; 2025: 12; 2026: 4.

122 papers.

Sort:

By area:

2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
2021Learning To Retrieve Prompts for In-Context Learningcited by 641
2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
2025Survey on Evaluation of LLM-based Agentscited by 190
2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
2023Compositional Exemplars for In-context Learningcited by 143
2023Unified Demonstration Retriever for In-Context Learningcited by 141
2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 136

38 more

2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 86
2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
2022META-GUI: Towards Multi-modal Conversational Agents on Mobile GUIcited by 81
2024CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automationcited by 70
2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 69
2024A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languagescited by 65
2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
2023Coverage-based Example Selection for In-Context Learningcited by 58
2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environmentscited by 57
2021Few-Shot Semantic Parsing with Language Models Trained On Codecited by 50
2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
2022ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answeringcited by 48
2021Improving Compositional Generalization with Latent Structure and Data Augmentationcited by 46
2021Communicating Natural Programs to Humans and Machinescited by 35
2021NL-EDIT: Correcting semantic parse errors through natural language interactioncited by 33
2022Calibrated Interpretation: Confidence Estimation in Semantic Parsingcited by 33
2025CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debuggingcited by 31
2023Decision-Oriented Dialogue for Human-AI Collaborationcited by 29
2024Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimizationcited by 29
2021Programming Puzzlescited by 25
2021Pretraining the Noisy Channel Model for Task-Oriented Dialoguecited by 23
2023Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniquescited by 23
2021ReasonBERT: Pre-trained to Reason with Distant Supervisioncited by 22
2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
2023L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Modelscited by 22
2021GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentationcited by 20
2023Learning to Simulate Natural Language Feedback for Interactive Semantic Parsingcited by 19
2023Improved Logical Reasoning of Language Models via Differentiable Symbolic Programmingcited by 18
2022Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue Systemcited by 16
2023PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogscited by 16
2021Towards Socially Intelligent Agents with Mental State Transition and Human Utilitycited by 14
2021Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQLcited by 13
2021On The Ingredients of an Effective Zero-shot Semantic Parsercited by 13
2023SUQL: Conversational Search over Structured and Unstructured Data with Large Language Modelscited by 13
2024Learning to Retrieve Iteratively for In-Context Learningcited by 13
2025Taxonomy of User Needs and Actionscited by 13

50 most cited of 122 All 122 (JSON)