BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

08/05/2022
by   Kurt Shuster, et al.
16

We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks. We release both the model weights and code, and have also deployed the model on a public web page to interact with organic users. This technical report describes how the model was built (architecture, model and training scheme), and details of its deployment, including safety mechanisms. Human evaluations show its superiority to existing open-domain dialogue agents, including its predecessors (Roller et al., 2021; Komeili et al., 2022). Finally, we detail our plan for continual learning using the data collected from deployment, which will also be publicly released. The goal of this research program is thus to enable the community to study ever-improving responsible agents that learn through interaction.

READ FULL TEXT

page 2

page 10

page 33

page 34

page 35

page 36

page 37

page 38

research
08/17/2019

Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack

The detection of offensive language in the context of a dialogue has bec...
research
07/15/2021

Internet-Augmented Dialogue Generation

The largest store of continually updating knowledge on our planet can be...
research
10/02/2020

Multi-Modal Open-Domain Dialogue

Recent work in open-domain conversational agents has demonstrated that s...
research
05/24/2019

Personalizing Dialogue Agents via Meta-Learning

Existing personalized dialogue models use human designed persona descrip...
research
08/05/2022

Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback

Frozen models trained to mimic static datasets can never improve their p...
research
06/22/2020

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

We present our view of what is necessary to build an engaging open-domai...
research
06/06/2022

Detecting Interlocutor Confusion in Situated Human-Avatar Dialogue: A Pilot Study

In order to enhance levels of engagement with conversational systems, ou...

Please sign up or login with your details

Forgot password? Click here to reset