Search Results for author:
Found 32 papers, 13 papers with code
Recipes for building an open-domain chatbot
Building open-domain chatbots is a challenging area for machine learning research.
Image Chat: Engaging Grounded Conversations
To test such models, we collect a dataset of grounded human-human conversations, where speakers are asked to play roles given a provided emotional mood or style, as the use of such traits is also a key factor in engagingness (Guo et al., 2019).
Ranked #2 on
Text Retrieval
on Image-Chat
Wizard of Wikipedia: Knowledge-Powered Conversational agents
In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date.
Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion
We show that, when using SeeKeR as a dialogue model, it outperforms the state-of-the-art model BlenderBot 2 (Chen et al., 2021) on open-domain knowledge-grounded conversations for the same number of parameters, in terms of consistency, knowledge and per-turn engagingness.
DIRECTOR: Generator-Classifiers For Supervised Language Modeling
Current language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness and contradictions.
BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
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 number of user defined tasks.
OPT: Open Pre-trained Transformer Language Models
Large language models, which are often trained for hundreds of thousands of compute days, have shown remarkable capabilities for zero- and few-shot learning.
Ranked #2 on
Stereotypical Bias Analysis
on CrowS-Pairs
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
The use of deep pre-trained bidirectional transformers has led to remarkable progress in a number of applications (Devlin et al., 2018).
Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
The use of deep pre-trained transformers has led to remarkable progress in a number of applications (Devlin et al., 2018).
Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills
Being engaging, knowledgeable, and empathetic are all desirable general qualities in a conversational agent.
Talk the Walk: Navigating New York City through Grounded Dialogue
We introduce "Talk The Walk", the first large-scale dialogue dataset grounded in action and perception.
The Second Conversational Intelligence Challenge (ConvAI2)
We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots.
OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization
To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks.
Ranked #26 on
Natural Language Inference
on RTE
Engaging Image Captioning Via Personality
While such tasks are useful to verify that a machine understands the content of an image, they are not engaging to humans as captions.
Talk The Walk: Navigating Grids in New York City through Grounded Dialogue
We introduce `"Talk The Walk", the first large-scale dialogue dataset grounded in action and perception.
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
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 utilizing knowledge resources, discuss topics and situations, and perceive and converse about images.
All-in-One Image-Grounded Conversational Agents
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 and talk becomes more feasible to explore.
Image-Chat: Engaging Grounded Conversations
To test such models, we collect a dataset of grounded human-human conversations, where speakers are asked to play roles given a provided emotional mood or style, as the use of such traits is also a key factor in engagingness (Guo et al., 2019).
Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
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 built so far, and the gaping holes we have not filled yet.
Deploying Lifelong Open-Domain Dialogue Learning
As argued in de Vries et al. (2020), crowdsourced data has the issues of lack of naturalness and relevance to real-world use cases, while the static dataset paradigm does not allow for a model to learn from its experiences of using language (Silver et al., 2013).
Multi-Modal Open-Domain Dialogue
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 both pre-training data and model size (Adiwardana et al., 2020; Roller et al., 2020).
Ranked #1 on
Visual Dialog
on Wizard of Wikipedia
Retrieval Augmentation Reduces Hallucination in Conversation
Despite showing increasingly human-like conversational abilities, state-of-the-art dialogue models often suffer from factual incorrectness and hallucination of knowledge (Roller et al., 2020).
Internet-Augmented Dialogue Generation
The largest store of continually updating knowledge on our planet can be accessed via internet search.
Reason first, then respond: Modular Generation for Knowledge-infused Dialogue
Large language models can produce fluent dialogue but often hallucinate factual inaccuracies.
Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity
State-of-the-art dialogue models still often stumble with regards to factual accuracy and self-contradiction.
When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels
Deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves.
The CRINGE Loss: Learning what language not to model
Standard language model training employs gold human documents or human-human interaction data, and treats all training data as positive examples.
Contrastive Distillation Is a Sample-Efficient Self-Supervised Loss Policy for Transfer Learning
Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional representations needed for generalization.
Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models
We compare models trained on our new dataset to existing pairwise-trained dialogue models, as well as large language models with few-shot prompting.
The HCI Aspects of Public Deployment of Research Chatbots: A User Study, Design Recommendations, and Open Challenges
Publicly deploying research chatbots is a nuanced topic involving necessary risk-benefit analyses.
Improving Open Language Models by Learning from Organic Interactions
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 system in order to improve both its skills and safety.
