Picture for Kurt Shuster

Kurt Shuster

The HCI Aspects of Public Deployment of Research Chatbots: A User Study, Design Recommendations, and Open Challenges

Add code
Jun 07, 2023
Viaarxiv icon

Improving Open Language Models by Learning from Organic Interactions

Add code
Jun 07, 2023
Viaarxiv icon

Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models

Add code
Apr 26, 2023
Viaarxiv icon

OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization

Add code
Dec 28, 2022
Viaarxiv icon

Contrastive Distillation Is a Sample-Efficient Self-Supervised Loss Policy for Transfer Learning

Add code
Dec 21, 2022
Viaarxiv icon

The CRINGE Loss: Learning what language not to model

Add code
Nov 10, 2022
Viaarxiv icon

When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels

Add code
Oct 28, 2022
Viaarxiv icon

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

Add code
Aug 10, 2022
Figure 1 for BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
Figure 2 for BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
Figure 3 for BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
Figure 4 for BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
Viaarxiv icon

DIRECTOR: Generator-Classifiers For Supervised Language Modeling

Add code
Jun 15, 2022
Figure 1 for DIRECTOR: Generator-Classifiers For Supervised Language Modeling
Figure 2 for DIRECTOR: Generator-Classifiers For Supervised Language Modeling
Figure 3 for DIRECTOR: Generator-Classifiers For Supervised Language Modeling
Figure 4 for DIRECTOR: Generator-Classifiers For Supervised Language Modeling
Viaarxiv icon

OPT: Open Pre-trained Transformer Language Models

Add code
May 05, 2022
Figure 1 for OPT: Open Pre-trained Transformer Language Models
Figure 2 for OPT: Open Pre-trained Transformer Language Models
Figure 3 for OPT: Open Pre-trained Transformer Language Models
Figure 4 for OPT: Open Pre-trained Transformer Language Models
Viaarxiv icon