# Proactive Dialogue Model with Intent Prediction

arXiv: https://arxiv.org/abs/2604.27379 · HTML: https://mlsanity.com/paper/2604.27379/

## 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 (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Gradient-Based Neural DAG Learning](https://mlsanity.com/paper/1906.02226/) (2019)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [Learning Sparse Nonparametric DAGs](https://mlsanity.com/paper/1909.13189/) (2019)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [DYNOTEARS: Structure Learning from Time-Series Data](https://mlsanity.com/paper/2002.00498/) (2020)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking](https://mlsanity.com/paper/2005.02877/) (2020)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement](https://mlsanity.com/paper/1911.08891/) (2019)
- [New Intent Discovery with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2205.12914/) (2022)
- [Learning the Structure of Dynamic Probabilistic Networks](https://mlsanity.com/paper/1301.7374/) (2013)
- [Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues](https://mlsanity.com/paper/2412.09049/) (2024)
- [Dialogue Language Model with Large-Scale Persona Data Engineering](https://mlsanity.com/paper/2412.09034/) (2024)
- [ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction](https://mlsanity.com/paper/2412.03075/) (2024)
- [QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation](https://mlsanity.com/paper/2505.05225/) (2025)
- [InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries](https://mlsanity.com/paper/2409.19689/) (2024)
- [Exploring the Impact of an LLM-Powered Teachable Agent on Learning Gains and Cognitive Load in Music Education](https://mlsanity.com/paper/2504.00636/) (2025)
- [Augmenting Compliance-Guaranteed Customer Service Chatbots: Context-Aware Knowledge Expansion with Large Language Models](https://mlsanity.com/paper/2410.12444/) (2024)
- [Neural-Bayesian Program Learning for Few-shot Dialogue Intent Parsing](https://mlsanity.com/paper/2410.06190/) (2024)
- [Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework](https://mlsanity.com/paper/2602.15377/) (2026)
- [Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognition](https://mlsanity.com/paper/2603.04945/) (2026)

## 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.