基本信息
views: 0
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
Bio
My research interests lie at the intersection of Natural Language Processing and Causal Inference. Despite remarkable performance on many natural language tasks, large language models tend to be obscured and susceptible to unforeseen flaws. The inscrutable nature of such models makes it difficult to discern if these models learn anything reasonable or rely on spurious correlation alone. Causality opens avenues in making systems interpretable to the users. In my research, I aspire to enrich interpretability, fairness, and trustworthiness by integrating causality in language systems.
Research Interests
Papers共 12 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
EMNLP 2023 (2023): 3313-3330
Conference on Empirical Methods in Natural Language Processing (2023): 11220-11237
Cited0Views0EIBibtex
0
0
arXiv (Cornell University) (2023)
Atanu R Sinha,Navita Goyal,Sunny Dhamnani, Tanay Asija, Raja K Dubey, M V Kaarthik Raja,Georgios Theocharous
arXiv (Cornell University) (2022)
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