Politically sensitive topics are still a challenge for open-domain chatbots. However, dealing with politically sensitive content in a responsible, non-partisan, and safe behavior way is integral for these chatbots. Currently, the main approach to handling political sensitivity is by simply changing such a topic when it is detected. This is safe but evasive and results in a chatbot that is less engaging. In this work, as a first step towards a politically safe chatbot, we propose a group of metrics for assessing their political prudence. We then conduct political prudence analysis of various chatbots and discuss their behavior from multiple angles through our automatic metric and human evaluation metrics. The testsets and codebase are released to promote research in this area.
@article{arxiv.2106.06157,
title = {Assessing Political Prudence of Open-domain Chatbots},
author = {Yejin Bang and Nayeon Lee and Etsuko Ishii and Andrea Madotto and Pascale Fung},
journal= {arXiv preprint arXiv:2106.06157},
year = {2021}
}
Comments
SIGDIAL 2021 - Safety for E2E Conversational AI (Camera-ready Version)