# Control in Hybrid Chatbots

arXiv: https://arxiv.org/abs/2311.11701 · HTML: https://mlsanity.com/paper/2311.11701/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 8 of 8)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [The Design and Implementation of XiaoIce, an Empathetic Social Chatbot](https://mlsanity.com/paper/1812.08989/) (2018)
- [Retrieve and Refine: Improved Sequence Generation Models For Dialogue](https://mlsanity.com/paper/1808.04776/) (2018)

## Abstract (arXiv)

Customer data typically is held in database systems, which can be seen as rule-based knowledge base, whereas businesses increasingly want to benefit from the capabilities of large, pre-trained language models. In this technical report, we describe a case study of how a commercial rule engine and an integrated neural chatbot may be integrated, and what level of control that particular integration mode leads to. We also discuss alternative ways (including past ways realized in other systems) how researchers strive to maintain control and avoid what has recently been called model "hallucination".