98 citations · 379 across the 21 of their papers we have counts for
21 papers · 1 filter
Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts
Mounica Maddela, Megan Ung, Jing Xu +3
Many cognitive approaches to well-being, such as recognizing and reframing unhelpful thoughts, have received considerable empirical support over the past decades, yet still lack tr…
Improving Open Language Models by Learning from Organic Interactions
Jing Xu, Da Ju, Joshua Lane +10
We present BlenderBot 3x, an update on the conversational model BlenderBot 3, which is now trained using organic conversation and feedback data from participating users of the syst…
Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
Jing Xu, Megan Ung, Mojtaba Komeili +3
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 hu…
BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
Kurt Shuster, Jing Xu, Mojtaba Komeili +15
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…
Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls
Da Ju, Jing Xu, Y-Lan Boureau +1
The promise of interaction between intelligent conversational agents and humans is that models can learn from such feedback in order to improve. Unfortunately, such exchanges in th…
Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents
Eric Michael Smith, Orion Hsu, Rebecca Qian +3
At the heart of improving conversational AI is the open problem of how to evaluate conversations. Issues with automatic metrics are well known (Liu et al., 2016, arXiv:1603.08023),…
SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
Megan Ung, Jing Xu, Y-Lan Boureau
Current open-domain conversational models can easily be made to talk in inadequate ways. Online learning from conversational feedback given by the conversation partner is a promisi…
Detecting Inspiring Content on Social Media
Oana Ignat, Y-Lan Boureau, Jane A. Yu +1
Inspiration moves a person to see new possibilities and transforms the way they perceive their own potential. Inspiration has received little attention in psychology, and has not b…
Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
Emily Dinan, Gavin Abercrombie, A. Stevie Bergman +4
Over the last several years, end-to-end neural conversational agents have vastly improved in their ability to carry a chit-chat conversation with humans. However, these models are…
Reducing conversational agents' overconfidence through linguistic calibration
Sabrina J. Mielke, Arthur Szlam, Emily Dinan +1
While improving neural dialogue agents' factual accuracy is the object of much research, another important aspect of communication, less studied in the setting of neural dialogue,…
Recipes for Safety in Open-domain Chatbots
Jing Xu, Da Ju, Margaret Li +3
Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted bi…
Controlling Style in Generated Dialogue
Eric Michael Smith, Diana Gonzalez-Rico, Emily Dinan +1
Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters. The vast training da…
Multi-scale Transformer Language Models
Sandeep Subramanian, Ronan Collobert, Marc'Aurelio Ranzato +1
We investigate multi-scale transformer language models that learn representations of text at multiple scales, and present three different architectures that have an inductive bias…
Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills
Eric Michael Smith, Mary Williamson, Kurt Shuster +2
Being engaging, knowledgeable, and empathetic are all desirable general qualities in a conversational agent. Previous work has introduced tasks and datasets that aim to help agents…
All-in-One Image-Grounded Conversational Agents
Da Ju, Kurt Shuster, Y-Lan Boureau +1
As single-task accuracy on individual language and image tasks has improved substantially in the last few years, the long-term goal of a generally skilled agent that can both see a…
Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles
Eric Michael Smith, Diana Gonzalez-Rico, Emily Dinan +1
Text style transfer is usually performed using attributes that can take a handful of discrete values (e.g., positive to negative reviews). In this work, we introduce an architectur…
Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
Margaret Li, Stephen Roller, Ilia Kulikov +4
Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely to…
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
Kurt Shuster, Da Ju, Stephen Roller +3
We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by u…
Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue
Dongyeop Kang, Anusha Balakrishnan, Pararth Shah +3
Traditional recommendation systems produce static rather than interactive recommendations invariant to a user's specific requests, clarifications, or current mood, and can suffer f…
Multiple-Attribute Text Style Transfer
Sandeep Subramanian, Guillaume Lample, Eric Michael Smith +3
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "styl…
Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset
Hannah Rashkin, Eric Michael Smith, Margaret Li +1
One challenge for dialogue agents is recognizing feelings in the conversation partner and replying accordingly, a key communicative skill. While it is straightforward for humans to…