Publicly deploying research chatbots is a nuanced topic involving necess...
We present BlenderBot 3x, an update on the conversational model BlenderB...
Current dialogue research primarily studies pairwise (two-party)
convers...
Recent work has shown that fine-tuning large pre-trained language models...
Traditional approaches to RL have focused on learning decision policies
...
Standard language model training employs gold human documents or human-h...
Deployed dialogue agents have the potential to integrate human feedback ...
We present BlenderBot 3, a 175B parameter dialogue model capable of
open...
Current language models achieve low perplexity but their resulting
gener...
Large language models, which are often trained for hundreds of thousands...
Language models (LMs) have recently been shown to generate more factual
...
State-of-the-art dialogue models still often stumble with regards to fac...
Large language models can produce fluent dialogue but often hallucinate
...
The largest store of continually updating knowledge on our planet can be...
Despite showing increasingly human-like conversational abilities,
state-...
Recent work in open-domain conversational agents has demonstrated that
s...
Much of NLP research has focused on crowdsourced static datasets and the...
We present our view of what is necessary to build an engaging open-domai...
Building open-domain chatbots is a challenging area for machine learning...
Being engaging, knowledgeable, and empathetic are all desirable general
...
As single-task accuracy on individual language and image tasks has impro...
We introduce dodecaDialogue: a set of 12 tasks that measures if a
conver...
The use of deep pretrained bidirectional transformers has led to remarka...
We describe the setting and results of the ConvAI2 NeurIPS competition t...
In open-domain dialogue intelligent agents should exhibit the use of
kno...
To achieve the long-term goal of machines being able to engage humans in...
Standard image captioning tasks such as COCO and Flickr30k are factual,
...
We introduce "Talk The Walk", the first large-scale dialogue dataset gro...