Our position paper “Hints of Independence in a Pre-scripted World: On Controlled Usage of Open-domain Language Models for Chatbots in Highly Sensitive Domains” is accepted to be published in the proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART). The publication also gained a spot in the conference for a poster presentation, which is going to take place on 3 February 2022.
Read the paper at https://doi.org/10.5220/0010914300003116
Title
Hints of Independence in a Pre-scripted World: On Controlled Usage of Open-domain Language Models for Chatbots in Highly Sensitive Domains
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.
Reference
Basar, E., Hendrickx, I., Krahmer, E., de Bruijn, G., & 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, pages 401-407.