58 citations · 84 across the 16 of their papers we have counts for
7 papers · 1 filter
Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI
Alex Mei, Sharon Levy, William Yang Wang
Users' physical safety is an increasing concern as the market for intelligent systems continues to grow, where unconstrained systems may recommend users dangerous actions that can…
WikiWhy: Answering and Explaining Cause-and-Effect Questions
Matthew Ho, Aditya Sharma, Justin Chang +4
As large language models (LLMs) grow larger and more sophisticated, assessing their "reasoning" capabilities in natural language grows more challenging. Recent question answering (…
SafeText: A Benchmark for Exploring Physical Safety in Language Models
Sharon Levy, Emily Allaway, Melanie Subbiah +4
Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such typ…
Mitigating Covertly Unsafe Text within Natural Language Systems
Alex Mei, Anisha Kabir, Sharon Levy +7
An increasingly prevalent problem for intelligent technologies is text safety, as uncontrolled systems may generate recommendations to their users that lead to injury or life-threa…
Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation
Samhita Honnavalli, Aesha Parekh, Lily Ou +4
Women are often perceived as junior to their male counterparts, even within the same job titles. While there has been significant progress in the evaluation of gender bias in natur…
HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data
Kai Nakamura, Sharon Levy, Yi-Lin Tuan +2
A pressing challenge in current dialogue systems is to successfully converse with users on topics with information distributed across different modalities. Previous work in multitu…