# Unsupervised Extraction of Dialogue Policies from Conversations

arXiv: https://arxiv.org/abs/2406.15214 · HTML: https://mlsanity.com/paper/2406.15214/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 21 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Benchmarking Natural Language Understanding Services for building Conversational Agents](https://mlsanity.com/paper/1903.05566/) (2019)
- [Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.00783/) (2021)
- [Rasa: Open Source Language Understanding and Dialogue Management](https://mlsanity.com/paper/1712.05181/) (2017)
- [Multi-document Summarization via Deep Learning Techniques: A Survey](https://mlsanity.com/paper/2011.04843/) (2020)
- [ConvLab: Multi-Domain End-to-End Dialog System Platform](https://mlsanity.com/paper/1904.08637/) (2019)
- [Intent Mining from past conversations for conversational agent](https://mlsanity.com/paper/2005.11014/) (2020)
- [ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction](https://mlsanity.com/paper/2106.10786/) (2021)
- [Unsupervised Dialog Structure Learning](https://mlsanity.com/paper/1904.03736/) (2019)
- [Workflow Discovery from Dialogues in the Low Data Regime](https://mlsanity.com/paper/2205.11690/) (2022)
- [QRFA: A Data-Driven Model of Information-Seeking Dialogues](https://mlsanity.com/paper/1812.10720/) (2018)
- [Unsupervised Learning of Hierarchical Conversation Structure](https://mlsanity.com/paper/2205.12244/) (2022)

## Built on by (most cited first, 3 of 3)

- [Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction](https://mlsanity.com/paper/2410.18481/) (2024)
- [RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates](https://mlsanity.com/paper/2506.11083/) (2025)
- [CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment](https://mlsanity.com/paper/2506.02264/) (2025)

## Abstract (arXiv)

Dialogue policies play a crucial role in developing task-oriented dialogue systems, yet their development and maintenance are challenging and typically require substantial effort from experts in dialogue modeling. While in many situations, large amounts of conversational data are available for the task at hand, people lack an effective solution able to extract dialogue policies from this data. In this paper, we address this gap by first illustrating how Large Language Models (LLMs) can be instrumental in extracting dialogue policies from datasets, through the conversion of conversations into a unified intermediate representation consisting of canonical forms. We then propose a novel method for generating dialogue policies utilizing a controllable and interpretable graph-based methodology. By combining canonical forms across conversations into a flow network, we find that running graph traversal algorithms helps in extracting dialogue flows. These flows are a better representation of the underlying interactions than flows extracted by prompting LLMs. Our technique focuses on giving conversation designers greater control, offering a productivity tool to improve the process of developing dialogue policies.