Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback. (arXiv:2208.03270v2 [cs.CL] UPDATED)

Frozen models trained to mimic static datasets can never improve their
performance. Models that can employ internet-retrieval for up-to-date
information and obtain feedback from humans during deployment provide the
promise of both adapting to new information, and improving their performance.
In this work we study how to improve internet-driven conversational skills in
such a learning framework. We collect deployment data, which we make publicly
available, of human interactions, and collect various types of human feedback
-- including binary quality measurements, …

arxiv deployment feedback human internet learning skills