Bot-Adversarial Dialogue for Safe Conversational Agents

Jing Xu, Da Ju, Margaret Li, Y-Lan Boureau, Jason Weston, Emily Dinan


Abstract
Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior. We introduce a new human-and-model-in-the-loop framework for evaluating the toxicity of such models, and compare a variety of existing methods in both the cases of non-adversarial and adversarial users that expose their weaknesses. We then go on to propose two novel methods for safe conversational agents, by either training on data from our new human-and-model-in-the-loop framework in a two-stage system, or ”baking-in” safety to the generative model itself. We find our new techniques are (i) safer than existing models; while (ii) maintaining usability metrics such as engagingness relative to state-of-the-art chatbots. In contrast, we expose serious safety issues in existing standard systems like GPT2, DialoGPT, and BlenderBot.
Anthology ID:
2021.naacl-main.235
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2950–2968
Language:
URL:
https://aclanthology.org/2021.naacl-main.235
DOI:
10.18653/v1/2021.naacl-main.235
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.235.pdf