# Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting

arXiv: https://arxiv.org/abs/2204.05610 · HTML: https://mlsanity.com/paper/2204.05610/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 12 Apr 2022.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [MASS: Masked Sequence to Sequence Pre-training for Language Generation](https://mlsanity.com/paper/1905.02450/) (2019)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [The Design and Implementation of XiaoIce, an Empathetic Social Chatbot](https://mlsanity.com/paper/1812.08989/) (2018)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)
- [Image Chat: Engaging Grounded Conversations](https://mlsanity.com/paper/1811.00945/) (2018)
- [Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features](https://mlsanity.com/paper/2107.06963/) (2021)
- [Deep Reinforcement Learning for Mention-Ranking Coreference Models](https://mlsanity.com/paper/1609.08667/) (2016)
- [Polite Dialogue Generation Without Parallel Data](https://mlsanity.com/paper/1805.03162/) (2018)
- [Low-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2002.10348/) (2020)
- [Hooks in the Headline: Learning to Generate Headlines with Controlled Styles](https://mlsanity.com/paper/2004.01980/) (2020)
- [Controlling Style in Generated Dialogue](https://mlsanity.com/paper/2009.10855/) (2020)
- [Zero-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2008.12918/) (2020)
- [Multimodal Dialogue Response Generation](https://mlsanity.com/paper/2110.08515/) (2021)
- [Structuring Latent Spaces for Stylized Response Generation](https://mlsanity.com/paper/1909.05361/) (2019)
- [Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory](https://mlsanity.com/paper/2004.02214/) (2020)
- [Topological Sort for Sentence Ordering](https://mlsanity.com/paper/2005.00432/) (2020)
- [Maria: A Visual Experience Powered Conversational Agent](https://mlsanity.com/paper/2105.13073/) (2021)
- [Open Domain Dialogue Generation with Latent Images](https://mlsanity.com/paper/2004.01981/) (2020)
- [Stylized Dialogue Response Generation Using Stylized Unpaired Texts](https://mlsanity.com/paper/2009.12719/) (2020)
- [StyleDGPT: Stylized Response Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.02569/) (2020)
- [Stylistic Dialogue Generation via Information-Guided Reinforcement Learning Strategy](https://mlsanity.com/paper/2004.02202/) (2020)

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

- [Style Vectors for Steering Generative Large Language Model](https://mlsanity.com/paper/2402.01618/) (2024)
- [KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2306.15430/) (2023)
- [One Agent to Serve All: a Lite-Adaptive Stylized AI Assistant for Millions of Multi-Style Official Accounts](https://mlsanity.com/paper/2509.17788/) (2025)
- [A Survey of Text Style Transfer: Applications and Ethical Implications](https://mlsanity.com/paper/2407.16737/) (2024)

## Abstract (arXiv)

Current Knowledge-Grounded Dialogue Generation (KDG) models specialize in producing rational and factual responses. However, to establish long-term relationships with users, the KDG model needs the capability to generate responses in a desired style or attribute. Thus, we study a new problem: Stylized Knowledge-Grounded Dialogue Generation (SKDG). It presents two challenges: (1) How to train a SKDG model where no <context, knowledge, stylized response> triples are available. (2) How to cohere with context and preserve the knowledge when generating a stylized response. In this paper, we propose a novel disentangled template rewriting (DTR) method which generates responses via combing disentangled style templates (from monolingual stylized corpus) and content templates (from KDG corpus). The entire framework is end-to-end differentiable and learned without supervision. Extensive experiments on two benchmarks indicate that DTR achieves a significant improvement on all evaluation metrics compared with previous state-of-the-art stylized dialogue generation methods. Besides, DTR achieves comparable performance with the state-of-the-art KDG methods in standard KDG evaluation setting.