6 papers
BASIL: Bayesian Assessment of Sycophancy in LLMs
Katherine Atwell, Pedram Heydari, Anthony Sicilia +1
Sycophancy (overly agreeable or flattering behavior) poses a fundamental challenge for human-AI collaboration, particularly in high-stakes decision-making domains such as health, l…
MixDPO: Modeling Preference Strength for Pluralistic Alignment
Saki Imai, Pedram Heydari, Anthony Sicilia +3
Preference based alignment objectives implicitly assume that all human preferences are expressed with equal strength. In practice, however, preference strength varies across indivi…
"Nothing about us without us": Perspectives of Global Deaf and Hard-of-hearing Community Members on Sign Language Technologies
Katherine Atwell, Saki Imai, Danielle Bragg +1
There is accelerating interest in sign language technologies (SLTs), with increasing attention from both industry and academia. However, the perspectives of Deaf and Hard-of-hearin…
Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI
Yuya Asano, Sabit Hassan, Paras Sharma +4
General-purpose automatic speech recognition (ASR) systems do not always perform well in goal-oriented dialogue. Existing ASR correction methods rely on prior user data or named en…
Generating Signed Language Instructions in Large-Scale Dialogue Systems
Mert Ä°nan, Katherine Atwell, Anthony Sicilia +2
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 m…
Studying and Mitigating Biases in Sign Language Understanding Models
Katherine Atwell, Danielle Bragg, Malihe Alikhani
Ensuring that the benefits of sign language technologies are distributed equitably among all community members is crucial. Thus, it is important to address potential biases and ine…