Alert button
Picture for Megan Ung

Megan Ung

Alert button

ROBBIE: Robust Bias Evaluation of Large Generative Language Models

Nov 29, 2023
David Esiobu, Xiaoqing Tan, Saghar Hosseini, Megan Ung, Yuchen Zhang, Jude Fernandes, Jane Dwivedi-Yu, Eleonora Presani, Adina Williams, Eric Michael Smith

Figure 1 for ROBBIE: Robust Bias Evaluation of Large Generative Language Models
Figure 2 for ROBBIE: Robust Bias Evaluation of Large Generative Language Models
Figure 3 for ROBBIE: Robust Bias Evaluation of Large Generative Language Models
Figure 4 for ROBBIE: Robust Bias Evaluation of Large Generative Language Models
Viaarxiv icon

Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts

Jul 06, 2023
Mounica Maddela, Megan Ung, Jing Xu, Andrea Madotto, Heather Foran, Y-Lan Boureau

Figure 1 for Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts
Figure 2 for Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts
Figure 3 for Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts
Figure 4 for Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts
Viaarxiv icon

Improving Open Language Models by Learning from Organic Interactions

Jun 07, 2023
Jing Xu, Da Ju, Joshua Lane, Mojtaba Komeili, Eric Michael Smith, Megan Ung, Morteza Behrooz, William Ngan, Rashel Moritz, Sainbayar Sukhbaatar, Y-Lan Boureau, Jason Weston, Kurt Shuster

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

Aug 16, 2022
Jing Xu, Megan Ung, Mojtaba Komeili, Kushal Arora, Y-Lan Boureau, Jason Weston

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

Aug 10, 2022
Kurt Shuster, Jing Xu, Mojtaba Komeili, Da Ju, Eric Michael Smith, Stephen Roller, Megan Ung, Moya Chen, Kushal Arora, Joshua Lane, Morteza Behrooz, William Ngan, Spencer Poff, Naman Goyal, Arthur Szlam, Y-Lan Boureau, Melanie Kambadur, Jason Weston

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

SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures

Oct 14, 2021
Megan Ung, Jing Xu, Y-Lan Boureau

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