mlsanityData to 14 Oct 2026

Proactive Dialogue Model with Intent Prediction

arXiv 2604.27379 ↗First posted 30 Apr 2026cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Dialogue models are inherently reactive, responding to the current user turn without anticipating upcoming intents, which leads to redundant interactions in multi-intent settings. We address this limitation by introducing a lightweight intent-transition prior derived from dialogue data and injected into the system prompt at inference time. We instantiate this prior using a Temporal Bayesian Network (T-BN) trained on per-turn intent annotations in MultiWOZ 2.2. The T-BN achieves Recall@5 = 0.787 and MRR = 0.576 on 1,071 held-out USER-turn pairs. In a ground-truth replay over 200 dialogues, BN-guided generation improves Coverage AUC from 0.742 to 0.856 and reduces the number of turns required to reach 75% intent coverage from 3.95 to 2.73. These results show that lightweight intent-transition guidance enables more proactive and efficient dialogue behavior without modifying the underlying language model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

28 of 37 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  3. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  4. 2020A Simple Language Model for Task-Oriented Dialoguecited by 332
  5. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  6. 2019Gradient-Based Neural DAG Learningcited by 227
  7. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  8. 2019Learning Sparse Nonparametric DAGscited by 207
  9. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 204
  10. 2020DYNOTEARS: Structure Learning from Time-Series Datacited by 200
  11. 2023Efficient Guided Generation for Large Language Modelscited by 200
  12. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
16 more
  1. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  2. 2023Large Language Models Enable Few-Shot Clusteringcited by 72
  3. 2023A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospectscited by 66
  4. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
  5. 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
  6. 2013Learning the Structure of Dynamic Probabilistic Networkscited by 12
  7. 2024Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialoguescited by 11
  8. 2024Dialogue Language Model with Large-Scale Persona Data Engineeringcited by 9
  9. 2024ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correctioncited by 7
  10. 2025QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluationcited by 5
  11. 2024InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Criescited by 4
  12. 2025Exploring the Impact of an LLM-Powered Teachable Agent on Learning Gains and Cognitive Load in Music Educationcited by 4
  13. 2024Augmenting Compliance-Guaranteed Customer Service Chatbots: Context-Aware Knowledge Expansion with Large Language Modelscited by 3
  14. 2024Neural-Bayesian Program Learning for Few-shot Dialogue Intent Parsingcited by 2
  15. 2026Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Frameworkcited by 1
  16. 2026Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognitioncited by 1

Built on by

Not cited yet.