Zobrazeno 1 - 10
of 1 078
pro vyhledávání: '"Kása, 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
\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
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
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:
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:
Dávid Sipos, Adorján Varga, Ágnes Kappéter, Bernadett Halda-Kiss, Péter Kása, Szilárd Pál, Béla Kocsis, Zoltán Péterfi
Publikováno v:
Frontiers in Cellular and Infection Microbiology, Vol 14 (2024)
IntroductionClostridioides difficile infections (CDI) continue to pose a challenge for clinicians. Fecal microbiota transplantation (FMT) is an effective treatment option in CDI. Furthermore, recent and ongoing studies suggest potential benefits of F
Externí odkaz:
https://doaj.org/article/6e5e52bc201a4fa6872c08cc725849af
Publikováno v:
Acta Universitatis Sapientiae: Informatica, Vol 15, Iss 2, Pp 267-293 (2023)
The graph realization problem seeks an answer to how and under what conditions a graph can be constructed if we know the degrees of its vertices. The problem was widely studied by many authors and in many ways, but there are still new ideas and solut
Externí odkaz:
https://doaj.org/article/ec9edca0bc7244eeb50fed0422ee6f1a
Autor:
Kása, Zoltán
In randomly created structures (be they natural or artificial) very often there exist ordered substructures. In this Hungarian language scientific essay we will present some of such structures in graph theory. E.g. R\'edei's theorem, Ramsey theory, T
Externí odkaz:
http://arxiv.org/abs/2112.02362