# Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations

arXiv: https://arxiv.org/abs/2604.18539 · HTML: https://mlsanity.com/paper/2604.18539/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning](https://mlsanity.com/paper/2305.13660/) (2023)
- [Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations](https://mlsanity.com/paper/2111.06647/) (2021)
- [Guiding attention in Sequence-to-sequence models for Dialogue Act prediction](https://mlsanity.com/paper/2002.08801/) (2020)
- [Dialogue Act Recognition via CRF-Attentive Structured Network](https://mlsanity.com/paper/1711.05568/) (2017)
- [Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation](https://mlsanity.com/paper/1808.10596/) (2018)
- [Regularizing Dialogue Generation by Imitating Implicit Scenarios](https://mlsanity.com/paper/2010.01893/) (2020)
- [Controllable Multi-Objective Re-ranking with Policy Hypernetworks](https://mlsanity.com/paper/2306.05118/) (2023)
- [Speaker-change Aware CRF for Dialogue Act Classification](https://mlsanity.com/paper/2004.02913/) (2020)
- [What Would a Teacher Do? Predicting Future Talk Moves](https://mlsanity.com/paper/2106.05249/) (2021)
- [TOD-Flow: Modeling the Structure of Task-Oriented Dialogues](https://mlsanity.com/paper/2312.04668/) (2023)
- [AI Systems in Text-Based Online Counselling: Ethical Considerations Across Three Implementation Approaches](https://mlsanity.com/paper/2601.08878/) (2026)
- [Evaluating Role-Consistency in LLMs for Counselor Training](https://mlsanity.com/paper/2601.08892/) (2026)

## Built on by (most cited first, 1 of 1)

- [GEMCo: A Validated, Ethically Releasable Proxy for Inaccessible Counselling Data](https://mlsanity.com/paper/2607.23621/) (2026)

## Abstract (arXiv)

This paper studies how empirical dialogue-flow statistics can be incorporated into Next Dialogue Act Prediction (NDAP). A KL regularization term is proposed that aligns predicted act distributions with corpus-derived transition patterns. Evaluated on a 60-class German counselling taxonomy using 5-fold cross-validation, this improves macro-F1 by 9--42% relative depending on encoder and substantially improves dialogue-flow alignment. Cross-dataset validation on HOPE suggests that improvements transfer across languages and counselling domains. In systematic ablations across pretrained encoders and architectures, the findings indicate that transition regularization provides consistent gains and disproportionately benefits weaker baseline models. The results suggest that lightweight discourse-flow priors complement pretrained encoders, especially in fine-grained, data-sparse dialogue tasks.