Picture for Y-Lan Boureau

Y-Lan Boureau

Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts

Add code
Jul 06, 2023
Viaarxiv icon

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

Add code
Jun 07, 2023
Figure 1 for The HCI Aspects of Public Deployment of Research Chatbots: A User Study, Design Recommendations, and Open Challenges
Figure 2 for The HCI Aspects of Public Deployment of Research Chatbots: A User Study, Design Recommendations, and Open Challenges
Viaarxiv icon

Improving Open Language Models by Learning from Organic Interactions

Add code
Jun 07, 2023
Figure 1 for Improving Open Language Models by Learning from Organic Interactions
Figure 2 for Improving Open Language Models by Learning from Organic Interactions
Figure 3 for Improving Open Language Models by Learning from Organic Interactions
Figure 4 for Improving Open Language Models by Learning from Organic Interactions
Viaarxiv icon

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

Add code
Aug 16, 2022
Figure 1 for Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
Figure 2 for Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
Figure 3 for Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
Figure 4 for Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
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

Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls

Add code
Aug 05, 2022
Figure 1 for Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls
Figure 2 for Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls
Figure 3 for Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls
Figure 4 for Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls
Viaarxiv icon

Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents

Add code
Jan 12, 2022
Figure 1 for Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents
Figure 2 for Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents
Figure 3 for Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents
Figure 4 for Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents
Viaarxiv icon

SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures

Add code
Oct 14, 2021
Figure 1 for SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
Figure 2 for SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
Figure 3 for SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
Figure 4 for SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
Viaarxiv icon

Detecting Inspiring Content on Social Media

Add code
Sep 06, 2021
Figure 1 for Detecting Inspiring Content on Social Media
Figure 2 for Detecting Inspiring Content on Social Media
Figure 3 for Detecting Inspiring Content on Social Media
Figure 4 for Detecting Inspiring Content on Social Media
Viaarxiv icon

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling

Add code
Jul 23, 2021
Figure 1 for Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
Figure 2 for Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
Figure 3 for Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
Figure 4 for Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
Viaarxiv icon