# Towards a Zero-Data, Controllable, Adaptive Dialog System

arXiv: https://arxiv.org/abs/2403.17582 · HTML: https://mlsanity.com/paper/2403.17582/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018)
- [Training Question Answering Models From Synthetic Data](https://mlsanity.com/paper/2002.09599/) (2020)
- [Recent Advances and Challenges in Task-oriented Dialog System](https://mlsanity.com/paper/2003.07490/) (2020)
- [Towards a Better Metric for Evaluating Question Generation Systems](https://mlsanity.com/paper/1808.10192/) (2018)
- [Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey](https://mlsanity.com/paper/2011.00564/) (2020)
- [Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference](https://mlsanity.com/paper/2011.10819/) (2020)
- [Self-Prompting Large Language Models for Zero-Shot Open-Domain QA](https://mlsanity.com/paper/2212.08635/) (2022)
- [Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning](https://mlsanity.com/paper/1702.03274/) (2017)
- [End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs](https://mlsanity.com/paper/2109.07263/) (2021)
- [Conversation Learner -- A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2004.04305/) (2020)
- [Conversational Tree Search: A New Hybrid Dialog Task](https://mlsanity.com/paper/2303.10227/) (2023)
- [Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation](https://mlsanity.com/paper/2306.04101/) (2023)
- [Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generation](https://mlsanity.com/paper/2305.01323/) (2023)

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

- [Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization](https://mlsanity.com/paper/2506.06964/) (2025)
- [A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents](https://mlsanity.com/paper/2601.10809/) (2026)
- [Investigating the effect of Mental Models in User Interaction with an Adaptive Dialog Agent](https://mlsanity.com/paper/2408.14154/) (2024)
- [Towards Zero-Shot, Controllable Dialog Planning with LLMs](https://mlsanity.com/paper/2410.05821/) (2024)

## Abstract (arXiv)

Conversational Tree Search (V"ath et al., 2023) is a recent approach to controllable dialog systems, where domain experts shape the behavior of a Reinforcement Learning agent through a dialog tree. The agent learns to efficiently navigate this tree, while adapting to information needs, e.g., domain familiarity, of different users. However, the need for additional training data hinders deployment in new domains. To address this, we explore approaches to generate this data directly from dialog trees. We improve the original approach, and show that agents trained on synthetic data can achieve comparable dialog success to models trained on human data, both when using a commercial Large Language Model for generation, or when using a smaller open-source model, running on a single GPU. We further demonstrate the scalability of our approach by collecting and testing on two new datasets: ONBOARD, a new domain helping foreign residents moving to a new city, and the medical domain DIAGNOSE, a subset of Wikipedia articles related to scalp and head symptoms. Finally, we perform human testing, where no statistically significant differences were found in either objective or subjective measures between models trained on human and generated data.