基本信息
views: 479
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
Bio
My research uses tools from statistics to make machine learning systems more robust and trustworthy — especially in complex systems such as large language models. The goal of my research is to use robustness and worst-case performance as a lens to understand and make progress on several fundamental challenges in machine learning and natural language processing. A few topics of recent interest are,
Long-tail behavior
How can we ensure that a machine learning system won't fail catastrophically in the wild under changing conditions?
Understanding
A system which understands how to answer questions or generate text should also do so robustly out-of-domain.
Fairness
Machine learning systems which rely on unreliable correlations can result in spurious and harmful predictions.
Long-tail behavior
How can we ensure that a machine learning system won't fail catastrophically in the wild under changing conditions?
Understanding
A system which understands how to answer questions or generate text should also do so robustly out-of-domain.
Fairness
Machine learning systems which rely on unreliable correlations can result in spurious and harmful predictions.
Research Interests
Papers共 128 篇Author StatisticsCo-AuthorSimilar Experts
By YearBy Citation主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
CoRR (2024)
Cited0Views0EIBibtex
0
0
CoRR (2024)
Cited0Views0EIBibtex
0
0
Cited0Views0EIBibtex
0
0
arxiv(2024)
Cited0Views0Bibtex
0
0
Christopher Mohri,Tatsunori Hashimoto
Cited0Views0EIBibtex
0
0
TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (2024): 39-57
CoRR (2024)
Cited0Views0EIBibtex
0
0
Yu Sun,Xinhao Li, Karan Dalal,Jiarui Xu, Arjun Vikram, Genghan Zhang,Yann Dubois,Xinlei Chen,Xiaolong Wang,Sanmi Koyejo,Tatsunori Hashimoto,Carlos Guestrin
arxiv(2024)
Cited0Views0Bibtex
0
0
Load More
Author Statistics
Co-Author
Co-Institution
D-Core
- 合作者
- 学生
- 导师
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn