Hints of Independence in a Pre-scripted World: On Controlled Usage of Open-domain Language Models for Chatbots in Highly Sensitive Domains

Erkan Başar, Iris Hendrickx, Emiel Krahmer, Gert-Jan de Bruijn, Gert-Jan de Bruijn, Tibor Bosse

2022

Abstract

Open-domain large language models have progressed to generating natural-sounding and coherent text. Even though the generated texts appear human-like, the main stumbling block is that their output is never fully predictable, which runs the risk of resulting in harmful content such as false statements or inflammatory language. This makes it difficult to apply these models in highly sensitive domains including personal health counselling. Hence, most of the chatbots for highly sensitive domains are developed using pre-scripted approaches. Although pre-scripted approaches are highly controlled, they suffer from repetitiveness and scalability issues. In this paper, we explore the possibility of combining the best of both worlds. We propose and describe in detail a new, flexible expert-driven hybrid architecture for harnessing the benefits of large language models in a controlled manner for highly sensitive domains and discuss the expectations and challenges.

Paper Citation

in Harvard Style

Başar E., Hendrickx I., Krahmer E., de Bruijn G. and Bosse T. (2022). Hints of Independence in a Pre-scripted World: On Controlled Usage of Open-domain Language Models for Chatbots in Highly Sensitive Domains. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-547-0, pages 401-407. DOI: 10.5220/0010914300003116

in Bibtex Style

@conference{icaart22,
author={Erkan Başar and Iris Hendrickx and Emiel Krahmer and Gert-Jan de Bruijn and Tibor Bosse},
title={Hints of Independence in a Pre-scripted World: On Controlled Usage of Open-domain Language Models for Chatbots in Highly Sensitive Domains},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2022},
pages={401-407},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010914300003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Hints of Independence in a Pre-scripted World: On Controlled Usage of Open-domain Language Models for Chatbots in Highly Sensitive Domains
SN - 978-989-758-547-0
AU - Başar E.
AU - Hendrickx I.
AU - Krahmer E.
AU - de Bruijn G.
AU - Bosse T.
PY - 2022
SP - 401
EP - 407
DO - 10.5220/0010914300003116