# Dialog Flow Induction for Constrainable LLM-Based Chatbots

arXiv: https://arxiv.org/abs/2408.01623 · HTML: https://mlsanity.com/paper/2408.01623/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 11 references that are in the map.
- First posted on arXiv 3 Aug 2024.

## Builds on (most cited first, 9 of 9)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Challenges in Building Intelligent Open-domain Dialog Systems](https://mlsanity.com/paper/1905.05709/) (2019)
- [Recent Advances and Challenges in Task-oriented Dialog System](https://mlsanity.com/paper/2003.07490/) (2020)
- [STAR: A Schema-Guided Dialog Dataset for Transfer Learning](https://mlsanity.com/paper/2010.11853/) (2020)
- [Schema-Guided Paradigm for Zero-Shot Dialog](https://mlsanity.com/paper/2106.07056/) (2021)
- [AnyTOD: A Programmable Task-Oriented Dialog System](https://mlsanity.com/paper/2212.09939/) (2022)
- [Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach](https://mlsanity.com/paper/1908.05854/) (2019)

## Built on by (most cited first, 4 of 4)

- [Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions](https://mlsanity.com/paper/2504.18474/) (2025)
- [Text-to-SQL Task-oriented Dialogue Ontology Construction](https://mlsanity.com/paper/2507.23358/) (2025)
- [A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents](https://mlsanity.com/paper/2601.10809/) (2026)
- [An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestration](https://mlsanity.com/paper/2609.07152/) (2026)

## Abstract (arXiv)

LLM-driven dialog systems are used in a diverse set of applications, ranging from healthcare to customer service. However, given their generalization capability, it is difficult to ensure that these chatbots stay within the boundaries of the specialized domains, potentially resulting in inaccurate information and irrelevant responses. This paper introduces an unsupervised approach for automatically inducing domain-specific dialog flows that can be used to constrain LLM-based chatbots. We introduce two variants of dialog flow based on the availability of in-domain conversation instances. Through human and automatic evaluation over various dialog domains, we demonstrate that our high-quality data-guided dialog flows achieve better domain coverage, thereby overcoming the need for extensive manual crafting of such flows.