Key-Value Retrieval Networks for Task-Oriented Dialogue
Not on the map. Why?
Abstract (arXiv)
Neural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base. In this work, we seek to address this problem by proposing a new neural dialogue agent that is able to effectively sustain grounded, multi-domain discourse through a novel key-value retrieval mechanism. The model is end-to-end differentiable and does not need to explicitly model dialogue state or belief trackers. We also release a new dataset of 3,031 dialogues that are grounded through underlying knowledge bases and span three distinct tasks in the in-car personal assistant space: calendar scheduling, weather information retrieval, and point-of-interest navigation. Our architecture is simultaneously trained on data from all domains and significantly outperforms a competitive rule-based system and other existing neural dialogue architectures on the provided domains according to both automatic and human evaluation metrics.
Key facts. Cited by 138 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 May 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2019: 1; 2020: 0; 2021: 31; 2022: 39; 2023: 35; 2024: 16; 2025: 11; 2026: 5.
138 papers.
Sort:
By area:
- 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
- 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
- 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
- 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
- 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
- 2021KLUE: Korean Language Understanding Evaluationcited by 114
- 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
- 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
- 2021Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systemscited by 75
- 2023SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agentscited by 71
- 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
- 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
38 more
- 2021BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modelingcited by 56
- 2022Controllable Dialogue Simulation with In-Context Learningcited by 42
- 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
- 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
- 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
- 2021GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systemscited by 31
- 2023Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Modelscited by 31
- 2021Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoringcited by 29
- 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
- 2022HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Datacited by 28
- 2022Neuro-Symbolic Procedural Planning with Commonsense Promptingcited by 28
- 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
- 2022Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Modelscited by 26
- 2023Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Studycited by 24
- 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
- 2023DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AIcited by 22
- 2021Structural Pre-training for Dialogue Comprehensioncited by 20
- 2021End-to-End Learning of Flowchart Grounded Task-Oriented Dialogscited by 20
- 2022DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generationcited by 19
- 2021Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue Systemcited by 18
- 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 17
- 2022Learning Dialogue Representations from Consecutive Utterancescited by 17
- 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directionscited by 17
- 2021NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulationcited by 16
- 2022Multimodal Conversational AI: A Survey of Datasets and Approachescited by 16
- 2022MVP: Multi-task Supervised Pre-training for Natural Language Generationcited by 16
- 2021Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classificationcited by 15
- 2022Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulatorcited by 15
- 2021CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detectioncited by 14
- 2022A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialogcited by 14
- 2023Through the Lens of Core Competency: Survey on Evaluation of Large Language Modelscited by 12
- 2021Conversational Entity Linking: Problem Definition and Datasetscited by 11
- 2021Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogscited by 11
- 2023Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representationcited by 11
- 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
- 2022Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systemscited by 10
- 2022Q-TOD: A Query-driven Task-oriented Dialogue Systemcited by 10
- 2023SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentationcited by 10
50 most cited of 138 All 138 (JSON)
- 2026CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking1 Oct 2026
- 2026Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation7 Aug 2026
- 2026Latent Preference Modeling for Multi-Session Personalized Tool Calling20 Apr 2026
- 2026CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation17 Mar 2026
- 2026ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling10 Mar 2026
- 2025Improving LLM's Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymization14 Nov 2025
- 2025RealTalk-CN: A Realistic Chinese Speech-Text Dialogue Benchmark With Cross-Modal Interaction Analysis6 Aug 2025
- 2025DRIVE: Disfluency-Rich Synthetic Dialog Data Generation Framework for Intelligent Vehicle Environments26 Jul 2025
- 2025Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems31 May 2025
- 2025DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset26 May 2025
- 2025clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations8 May 2025
- 2025PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona24 Apr 2025
38 more
- 2025Efficient Intent-Based Filtering for Multi-Party Conversations Using Knowledge Distillation from LLMs21 Mar 2025
- 2025MonoTODia: Translating Monologue Requests to Task-Oriented Dialogues24 Feb 2025
- 2025What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects24 Jan 2025
- 2025Rethinking Table Instruction Tuning24 Jan 2025
- 2024SCOUT: A Situated and Multi-Modal Human-Robot Dialogue Corpus19 Nov 2024
- 2024Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch24 Oct 2024
- 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunities17 Jul 2024
- 2024Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue20 Jun 2024
- 2024Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systems10 Jun 2024
- 2024Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue30 May 2024
- 2024Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems24 May 2024
- 2024DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations31 Mar 2024
- 2024RECIPE4U: Student-ChatGPT Interaction Dataset in EFL Writing Education13 Mar 2024
- 2024BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses2 Mar 2024
- 2024LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues1 Mar 2024
- 2024Memory-Augmented Generative Adversarial Transformers29 Feb 2024
- 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems28 Feb 2024
- 2024StructLM: Towards Building Generalist Models for Structured Knowledge Grounding26 Feb 2024
- 2024Pro-HAN: A Heterogeneous Graph Attention Network for Profile-Based Spoken Language Understanding6 Feb 2024
- 2024DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models4 Jan 2024
- 2023OmniDialog: An Omnipotent Pre-training Model for Task-Oriented Dialogue System28 Dec 2023
- 2023Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisations21 Dec 2023
- 2023CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs29 Nov 2023
- 2023TableLlama: Towards Open Large Generalist Models for Tables15 Nov 2023
- 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions15 Nov 2023
- 2023A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human-Robot Interaction3 Nov 2023
- 2023IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems2 Nov 2023
- 2023Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems23 Oct 2023
- 2023Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance Scoring20 Oct 2023
- 2023InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems13 Oct 2023
- 2023Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System13 Oct 2023
- 2023Testing the Limits of Unified Sequence to Sequence LLM Pretraining on Diverse Table Data Tasks1 Oct 2023
- 2023A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training1 Oct 2023
- 2023UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt20 Sep 2023
- 2023Multi-turn Dialogue Comprehension from a Topic-aware Perspective18 Sep 2023
- 2023Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extraction16 Aug 2023
- 2023Through the Lens of Core Competency: Survey on Evaluation of Large Language Models15 Aug 2023
- 2023DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI19 Jul 2023
50 newest of 138 All 138 (JSON)
- 2023Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Modelscited by 31
- 2022Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systemscited by 10
- 2025Rethinking Table Instruction Tuningcited by 10
- 2022An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generationcited by 5
- 2023Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance Scoringcited by 1
- 2022Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialogcited by 0
- 2025Rethinking Table Instruction Tuning24 Jan 2025
- 2023Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance Scoring20 Oct 2023
- 2023Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models29 May 2023
- 2022Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog13 Oct 2022
- 2022Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems20 Mar 2022
- 2022An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation11 Mar 2022
- 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
- 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
- 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
- 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
- 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
- 2021KLUE: Korean Language Understanding Evaluationcited by 114
- 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
- 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
- 2021Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systemscited by 75
- 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
- 2021BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modelingcited by 56
- 2022Controllable Dialogue Simulation with In-Context Learningcited by 42
12 most cited of 123 All 123 (JSON)
- 2026CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking1 Oct 2026
- 2026Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation7 Aug 2026
- 2026ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling10 Mar 2026
- 2025Improving LLM's Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymization14 Nov 2025
- 2025RealTalk-CN: A Realistic Chinese Speech-Text Dialogue Benchmark With Cross-Modal Interaction Analysis6 Aug 2025
- 2025DRIVE: Disfluency-Rich Synthetic Dialog Data Generation Framework for Intelligent Vehicle Environments26 Jul 2025
- 2025Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems31 May 2025
- 2025DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset26 May 2025
- 2025clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations8 May 2025
- 2025PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona24 Apr 2025
- 2025MonoTODia: Translating Monologue Requests to Task-Oriented Dialogues24 Feb 2025
- 2025What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects24 Jan 2025
12 newest of 123 All 123 (JSON)