papers

Publications (29)

cs.CL2020

Recipes for building an open-domain chatbot

Stephen Roller, Emily Dinan, Naman Goyal +9

Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of…

cs.AI2021

Internet-Augmented Dialogue Generation

Mojtaba Komeili, Kurt Shuster, Jason Weston

The largest store of continually updating knowledge on our planet can be accessed via internet search. In this work we study giving access to this information to conversational age…

cs.CL2020

Multi-Modal Open-Domain Dialogue

Kurt Shuster, Eric Michael Smith, Da Ju +1

Recent work in open-domain conversational agents has demonstrated that significant improvements in model engagingness and humanness metrics can be achieved via massive scaling in b…

cs.CL2023

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

Srinivasan Iyer, Xi Victoria Lin, Ramakanth Pasunuru +15

Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few…

cs.CL2022

OPT: Open Pre-trained Transformer Language Models

Susan Zhang, Stephen Roller, Naman Goyal +16

Large language models, which are often trained for hundreds of thousands of compute days, have shown remarkable capabilities for zero- and few-shot learning. Given their computatio…

cs.CL2020

Image Chat: Engaging Grounded Conversations

Kurt Shuster, Samuel Humeau, Antoine Bordes +1

To achieve the long-term goal of machines being able to engage humans in conversation, our models should captivate the interest of their speaking partners. Communication grounded i…

cs.CL2023

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

Jimmy Wei, Kurt Shuster, Arthur Szlam +3

Current dialogue research primarily studies pairwise (two-party) conversations, and does not address the everyday setting where more than two speakers converse together. In this wo…

cs.CL2020

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

Stephen Roller, Y-Lan Boureau, Jason Weston +13

We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been bui…

cs.CL2021

Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity

Kurt Shuster, Jack Urbanek, Arthur Szlam +1

State-of-the-art dialogue models still often stumble with regards to factual accuracy and self-contradiction. Anecdotally, they have been observed to fail to maintain character ide…

cs.CV2019

Engaging Image Captioning Via Personality

Kurt Shuster, Samuel Humeau, Hexiang Hu +2

Standard image captioning tasks such as COCO and Flickr30k are factual, neutral in tone and (to a human) state the obvious (e.g., "a man playing a guitar"). While such tasks are us…

cs.AI2023

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

Morteza Behrooz, William Ngan, Joshua Lane +8

Publicly deploying research chatbots is a nuanced topic involving necessary risk-benefit analyses. While there have recently been frequent discussions on whether it is responsible…

cs.AI2019

The Second Conversational Intelligence Challenge (ConvAI2)

Emily Dinan, Varvara Logacheva, Valentin Malykh +14

We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots. Some key takeaways from the competition ar…

cs.CL2022

DIRECTOR: Generator-Classifiers For Supervised Language Modeling

Kushal Arora, Kurt Shuster, Sainbayar Sukhbaatar +1

Current language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness and contradictions. The standard language modeling…

cs.CL2022

Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion

Kurt Shuster, Mojtaba Komeili, Leonard Adolphs +3

Language models (LMs) have recently been shown to generate more factual responses by employing modularity (Zhou et al., 2021) in combination with retrieval (Adolphs et al., 2021).…

cs.AI2020

Deploying Lifelong Open-Domain Dialogue Learning

Kurt Shuster, Jack Urbanek, Emily Dinan +2

Much of NLP research has focused on crowdsourced static datasets and the supervised learning paradigm of training once and then evaluating test performance. As argued in de Vries e…

cs.CL2022

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

Chris Lengerich, Gabriel Synnaeve, Amy Zhang +4

Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional repres…

cs.CL2022

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

Weiyan Shi, Emily Dinan, Kurt Shuster +2

Deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves. However, humans may not always provide explicit signals when the chatbot…

cs.CL2020

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…

cs.CL2019

Wizard of Wikipedia: Knowledge-Powered Conversational agents

Emily Dinan, Stephen Roller, Kurt Shuster +3

In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date. The most popular sequence to sequen…

cs.CL2022

The CRINGE Loss: Learning what language not to model

Leonard Adolphs, Tianyu Gao, Jing Xu +3

Standard language model training employs gold human documents or human-human interaction data, and treats all training data as positive examples. Growing evidence shows that even w…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2022

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…

cs.CL2021

Reason first, then respond: Modular Generation for Knowledge-infused Dialogue

Leonard Adolphs, Kurt Shuster, Jack Urbanek +2

Large language models can produce fluent dialogue but often hallucinate factual inaccuracies. While retrieval-augmented models help alleviate this issue, they still face a difficul…

cs.CL2020

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…

cs.AI2018

Talk the Walk: Navigating New York City through Grounded Dialogue

Harm de Vries, Kurt Shuster, Dhruv Batra +3

We introduce "Talk The Walk", the first large-scale dialogue dataset grounded in action and perception. The task involves two agents (a "guide" and a "tourist") that communicate vi…

cs.CL2020

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…

cs.CL2021

Retrieval Augmentation Reduces Hallucination in Conversation

Kurt Shuster, Spencer Poff, Moya Chen +2

Despite showing increasingly human-like conversational abilities, state-of-the-art dialogue models often suffer from factual incorrectness and hallucination of knowledge (Roller et…

cs.CL2023

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…

cs.CL2020

Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring

Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux +1

The use of deep pre-trained bidirectional transformers has led to remarkable progress in a number of applications (Devlin et al., 2018). For tasks that make pairwise comparisons be…