# Sketch-Fill-A-R: A Persona-Grounded Chit-Chat Generation Framework

arXiv: https://arxiv.org/abs/1910.13008 · HTML: https://mlsanity.com/paper/1910.13008/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 8 of 8)

- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Faithful Persona-based Conversational Dataset Generation with Large Language Models](https://mlsanity.com/paper/2312.10007/) (2023)
- [Learning to Complete Code with Sketches](https://mlsanity.com/paper/2106.10158/) (2021)
- [A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles](https://mlsanity.com/paper/2102.08322/) (2021)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Characteristic AI Agents via Large Language Models](https://mlsanity.com/paper/2403.12368/) (2024)
- [Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems](https://mlsanity.com/paper/2307.07255/) (2023)
- [Persona-Aware Alignment Framework for Personalized Dialogue Generation](https://mlsanity.com/paper/2511.10215/) (2025)

## Abstract (arXiv)

Human-like chit-chat conversation requires agents to generate responses that are fluent, engaging and consistent. We propose Sketch-Fill-A-R, a framework that uses a persona-memory to generate chit-chat responses in three phases. First, it generates dynamic sketch responses with open slots. Second, it generates candidate responses by filling slots with parts of its stored persona traits. Lastly, it ranks and selects the final response via a language model score. Sketch-Fill-A-R outperforms a state-of-the-art baseline both quantitatively (10-point lower perplexity) and qualitatively (preferred by 55% heads-up in single-turn and 20% higher in consistency in multi-turn user studies) on the Persona-Chat dataset. Finally, we extensively analyze Sketch-Fill-A-R's responses and human feedback, and show it is more consistent and engaging by using more relevant responses and questions.