Alert button
Picture for Mojtaba Komeili

Mojtaba Komeili

Alert button

Chain-of-Verification Reduces Hallucination in Large Language Models

Sep 25, 2023
Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, Jason Weston

Figure 1 for Chain-of-Verification Reduces Hallucination in Large Language Models
Figure 2 for Chain-of-Verification Reduces Hallucination in Large Language Models
Figure 3 for Chain-of-Verification Reduces Hallucination in Large Language Models
Figure 4 for Chain-of-Verification Reduces Hallucination in Large Language Models
Viaarxiv icon

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

Jun 07, 2023
Morteza Behrooz, William Ngan, Joshua Lane, Giuliano Morse, Benjamin Babcock, Kurt Shuster, Mojtaba Komeili, Moya Chen, Melanie Kambadur, Y-Lan Boureau, Jason Weston

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

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

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

Apr 26, 2023
Jimmy Wei, Kurt Shuster, Arthur Szlam, Jason Weston, Jack Urbanek, Mojtaba Komeili

Figure 1 for Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models
Figure 2 for Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models
Figure 3 for Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models
Figure 4 for Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models
Viaarxiv icon

Infusing Commonsense World Models with Graph Knowledge

Jan 13, 2023
Alexander Gurung, Mojtaba Komeili, Arthur Szlam, Jason Weston, Jack Urbanek

Figure 1 for Infusing Commonsense World Models with Graph Knowledge
Figure 2 for Infusing Commonsense World Models with Graph Knowledge
Figure 3 for Infusing Commonsense World Models with Graph Knowledge
Figure 4 for Infusing Commonsense World Models with Graph Knowledge
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