Search Results for author:
Found 20 papers, 10 papers with code
Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems
While theories of discourse and cognitive science have long recognized the value of unhurried pacing, recent dialogue research tends to minimize friction in conversational systems.
Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI
Evaluated in home improvement and cooking domains with real-world users, our method improves recall and F1 of correction by 34% and 16%, respectively, while maintaining precision and false positive rate.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
An Active Learning Framework for Inclusive Generation by Large Language Models
We address this challenge with a novel clustering-based active learning framework, enhanced with knowledge distillation.
Accounting for Sycophancy in Language Model Uncertainty Estimation
From these results, we argue that externalizing both model and user uncertainty can help to mitigate the impacts of sycophancy bias.
Generating Signed Language Instructions in Large-Scale Dialogue Systems
We introduce a goal-oriented conversational AI system enhanced with American Sign Language (ASL) instructions, presenting the first implementation of such a system on a worldwide multimodal conversational AI platform.
Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors
For instance, it can be applied in social media moderation to predict harmful user behaviors before they occur, allowing for preventative interventions.
Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios
Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems.
Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecasting
Typically, when evaluating Theory of Mind, we consider the beliefs of others to be binary: held or not held.
Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models
Effective interlocutors account for the uncertain goals, beliefs, and emotions of others.
Learning to Generate Equitable Text in Dialogue from Biased Training Data
Absence of equitable and inclusive principles can hinder the formation of common ground, which in turn negatively impacts the overall performance of the system.
HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations
While demographic factors like age and gender change the way people talk, and in particular, the way people talk to machines, there is little investigation into how large pre-trained language models (LMs) can adapt to these changes.
LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue
From this insight, we propose a new algorithm, and empirically, we demonstrate our proposal improves both task-success and human-likeness of the generated text.
Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights
We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies.
PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners
Multiclass neural networks are a common tool in modern unsupervised domain adaptation, yet an appropriate theoretical description for their non-uniform sample complexity is lacking in the adaptation literature.
Test-time Fourier Style Calibration for Domain Generalization
Thus, it is still possible that those methods can overfit to source domains and perform poorly on target domains.
The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error
Our results not only motivate our proposal and help us to understand its limitations, but also provide insight on the properties of discourse models and datasets which improve performance in domain adaptation.
PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging
Application of deep neural networks to medical imaging tasks has in some sense become commonplace.
Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning
We consider a model-agnostic solution to the problem of Multi-Domain Learning (MDL) for multi-modal applications.
Robust White Matter Hyperintensity Segmentation on Unseen Domain
That is, we train on samples from a set of distributions (sources) and test on samples from a new, unseen distribution (target).
Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve
Further, this theory has been well-used in practice.
