Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Xiu, Zidi"'
As modern Large Language Models (LLMs) shatter many state-of-the-art benchmarks in a variety of domains, this paper investigates their behavior in the domains of ethics and fairness, focusing on protected group bias. We conduct a two-part study: firs
Externí odkaz:
http://arxiv.org/abs/2403.14727
Autor:
Sun, David Q., Abzaliev, Artem, Kotek, Hadas, Xiu, Zidi, Klein, Christopher, Williams, Jason D.
Controversy is a reflection of our zeitgeist, and an important aspect to any discourse. The rise of large language models (LLMs) as conversational systems has increased public reliance on these systems for answers to their various questions. Conseque
Externí odkaz:
http://arxiv.org/abs/2310.18130
Autor:
Xiu, Zidi, Cheng, Kai-Chen, Sun, David Q., Lu, Jiannan, Kotek, Hadas, Zhang, Yuhan, McCarthy, Paul, Klein, Christopher, Pulman, Stephen, Williams, Jason D.
With the growing popularity of intelligent assistants (IAs), evaluating IA quality becomes an increasingly active field of research. This paper identifies and quantifies the feedback effect, a novel component in IA-user interactions: how the capabili
Externí odkaz:
http://arxiv.org/abs/2303.10255
The recent introduction of thermodynamic integration techniques has provided a new framework for understanding and improving variational inference (VI). In this work, we present a careful analysis of the thermodynamic variational objective (TVO), bri
Externí odkaz:
http://arxiv.org/abs/2111.02947
Dealing with severe class imbalance poses a major challenge for real-world applications, especially when the accurate classification and generalization of minority classes is of primary interest. In computer vision, learning from long tailed datasets
Externí odkaz:
http://arxiv.org/abs/2011.12454
Autor:
Xiu, Zidi, Tao, Chenyang, Gao, Michael, Davis, Connor, Goldstein, Benjamin A., Henao, Ricardo
Combining the increasing availability and abundance of healthcare data and the current advances in machine learning methods have created renewed opportunities to improve clinical decision support systems. However, in healthcare risk prediction applic
Externí odkaz:
http://arxiv.org/abs/2009.08541
The abundance of modern health data provides many opportunities for the use of machine learning techniques to build better statistical models to improve clinical decision making. Predicting time-to-event distributions, also known as survival analysis
Externí odkaz:
http://arxiv.org/abs/2003.04430
Autor:
Chen, Junya, Xiu, Zidi, Goldstein, Benjamin A., Henao, Ricardo, Carin, Lawrence, Tao, Chenyang
Publikováno v:
Adv Neural Inf Process Syst
Dealing with severe class imbalance poses a major challenge for many real-world applications, especially when the accurate classification and generalization of minority classes are of primary interest. In computer vision and NLP, learning from datase
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cb2d611936c9e2743f43c2eb651a6adf
http://arxiv.org/abs/2011.12454
http://arxiv.org/abs/2011.12454
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
