Zobrazeno 1 - 10
of 1 230
pro vyhledávání: '"Kasa, P."'
Large Language Models (LLMs) have seen widespread adoption due to their remarkable natural language capabilities. However, when deploying them in real-world settings, it is important to align LLMs to generate texts according to acceptable human stand
Externí odkaz:
http://arxiv.org/abs/2407.06443
Conformal prediction (CP) enables machine learning models to output prediction sets with guaranteed coverage rate, assuming exchangeable data. Unfortunately, the exchangeability assumption is frequently violated due to distribution shifts in practice
Externí odkaz:
http://arxiv.org/abs/2406.01416
Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques
Autor:
Kasa, Siva Rajesh, Goel, Aniket, Gupta, Karan, Roychowdhury, Sumegh, Bhanushali, Anish, Pattisapu, Nikhil, Murthy, Prasanna Srinivasa
Ordinal Classification (OC) is a widely encountered challenge in Natural Language Processing (NLP), with applications in various domains such as sentiment analysis, rating prediction, and more. Previous approaches to tackle OC have primarily focused
Externí odkaz:
http://arxiv.org/abs/2405.11775
\texttt{Mixture-Models} is an open-source Python library for fitting Gaussian Mixture Models (GMM) and their variants, such as Parsimonious GMMs, Mixture of Factor Analyzers, MClust models, Mixture of Student's t distributions, etc. It streamlines th
Externí odkaz:
http://arxiv.org/abs/2402.10229
Autor:
Gupta, Karan, Roychowdhury, Sumegh, Kasa, Siva Rajesh, Kasa, Santhosh Kumar, Bhanushali, Anish, Pattisapu, Nikhil, Murthy, Prasanna Srinivasa
In the In-Context Learning (ICL) setup, various forms of label biases can manifest. One such manifestation is majority label bias, which arises when the distribution of labeled examples in the in-context samples is skewed towards one or more specific
Externí odkaz:
http://arxiv.org/abs/2312.16549
Autor:
Roychowdhury, Sumegh, Gupta, Karan, Kasa, Siva Rajesh, Murthy, Prasanna Srinivasa, Chandra, Alok
Publikováno v:
NeurIPS 2023 - Workshop on Distribution Shifts
Pre-trained language models (PLMs) have seen tremendous success in text classification (TC) problems in the context of Natural Language Processing (NLP). In many real-world text classification tasks, the class definitions being learned do not remain
Externí odkaz:
http://arxiv.org/abs/2311.03320
Autor:
Habtu Debash, Agumas Shibabaw, Hussen Ebrahim, Mihret Tilahun, Abdurahaman Seid, Getnet Shimeles, Birhanu Kassanew, Ermiyas Alemayehu, Yeshimebet Kasa, Sisay Desale, Amanuel Mengesha, Alemu Gedefie
Publikováno v:
BMC Infectious Diseases, Vol 24, Iss 1, Pp 1-10 (2024)
Abstract Background Scabies disproportionately affects people in resource-poor areas. Clinical diagnosis risks misdiagnosis due to resemblance to other skin diseases, but laboratory confirmation improves accuracy. Scabies allow for secondary bacteria
Externí odkaz:
https://doaj.org/article/d18cb0cea85649de9a672e6822771386
Autor:
Abraham Solomon Kasa, Dinsefa Mensur Andoshe, Noto Susanto Gultom, Dong-Hau Kuo, Xiaoyun Chen, Hairus Abdullah, Osman Ahmed Zelekew
Publikováno v:
Applied Water Science, Vol 14, Iss 9, Pp 1-13 (2024)
Abstract Noble metal-free nickel manganese oxysulfide (NiMnOS) catalysts were successfully prepared via a facile and eco-friendly approach at a low synthesis temperature of 90 °C in a water bath. The catalysts were synthesized by varying Ni: Mn mola
Externí odkaz:
https://doaj.org/article/9b64bfc16f3e434eb2c4422a02a02d49
Autor:
Kasa, Kevin, Taylor, Graham W.
Conformal prediction has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. Yet, its performance is known to degrade under distribution shift and long-tailed class distributions, w
Externí odkaz:
http://arxiv.org/abs/2307.01088
Autor:
Ziyandiswa Fono, Luvo Kasa
Publikováno v:
E-Journal of Humanities, Arts and Social Sciences, Vol 5, Iss 7, Pp 1339-1350 (2024)
The study addresses the critical and pervasive issue of gender-based violence (GBV), a universal human rights violation affecting individuals across the globe, irrespective of cultural, socioeconomic, or religious backgrounds. While GBV predominantly
Externí odkaz:
https://doaj.org/article/008184fe3d904eaa977fca3980edcdcb