Zobrazeno 1 - 10
of 9 997
pro vyhledávání: '"Sasse OR"'
As Vision Language Models (VLMs) gain widespread use, their fairness remains under-explored. In this paper, we analyze demographic biases across five models and six datasets. We find that portrait datasets like UTKFace and CelebA are the best tools f
Externí odkaz:
http://arxiv.org/abs/2410.13146
Federated Kolmogorov-Arnold Networks (F-KANs) have already been proposed, but their assessment is at an initial stage. We present a comparison between KANs (using B-splines and Radial Basis Functions as activation functions) and Multi- Layer Perceptr
Externí odkaz:
http://arxiv.org/abs/2410.08961
Background: Machine learning methods for clinical named entity recognition and entity normalization systems can utilize both labeled corpora and Knowledge Graphs (KGs) for learning. However, infrequently occurring concepts may have few mentions in tr
Externí odkaz:
http://arxiv.org/abs/2410.07951
Autor:
Chen, Shan, Gao, Mingye, Sasse, Kuleen, Hartvigsen, Thomas, Anthony, Brian, Fan, Lizhou, Aerts, Hugo, Gallifant, Jack, Bitterman, Danielle
Background: Large language models (LLMs) are trained to follow directions, but this introduces a vulnerability to blindly comply with user requests even if they generate wrong information. In medicine, this could accelerate the generation of misinfor
Externí odkaz:
http://arxiv.org/abs/2409.20385
Autor:
Herpich, Fabio R., Almeida-Fernandes, Felipe, Schwarz, Gustavo B. Oliveira, Lima, Erik V. R., Nakazono, Lilianne, Alonso-García, Javier, Fonseca-Faria, Marcos A., Sartori, Marilia J., Bolutavicius, Guilherme F., de Souza, Gabriel Fabiano, Hartmann, Eduardo A., Li, Liana, Espinosa, Luna, Kanaan, Antonio, Schoenell, William, Werle, Ariel, Machado-Pereira, Eduardo, Gutiérrez-Soto, Luis A., Santos-Silva, Thaís, Castelli, Analia V. Smith, Lacerda, Eduardo A. D., Barbosa, Cassio L., Perottoni, Hélio D., Lopes, Carlos E. Ferreira, Valença, Raquel Ruiz, Martho, Pierre Augusto Re, Bom, Clecio R., Bonatto, Charles J., Carvalho, Maiara S., Cernic, Vitor, Fernandes, Roberto Cid, Coelho, Paula, Cortesi, Ariana, Palma, Barbara Cubillos, Doubrawa, Lia, Alberice, Vincenzo Sivero Ferreira, Huaynasi, Fredi Quispe, Perin, Gabriel Jacob, Arancibia, Marcelo Jaque, Krabbe, Angela, Lima-Dias, Ciria, Lomelí-Núñez, Luis, de Oliveira, Raimundo Lopes, Lopes, Amanda R., Figueiredo, André Luiz, Lösch, Elismar, Navarete, Felipe, de Oliveira, Julia Mello, Overzier, Roderik, Placco, Vinicius M., Roig, Fernando V., Rubet, Mariana, Santos, André, Sasse, Victor Hugo, Thaina-Batista, Julia, Torres-Flores, Sergio, Beers, Timothy C., Alvarez-Candal, Alvaro, Akras, Stavros, Panda, Swayamtrupta, Limberg, Guilherme, Castellón, José Luis Nilo, Telles, Eduardo, Lopes, Paulo Afranio, Montaguth, Gissel Dayana Pardo, Silva, Leandro Beraldo e, Humire, Pedro K., Fernandes, Marcelo Borges, Cordeiro, Vinícius, Ribeiro, Tiago, de Oliveira, Claudia Mendes
The Southern Photometric Local Universe Survey (S-PLUS) is a project to map $\sim9300$ sq deg of the sky using twelve bands (seven narrow and five broadbands). Observations are performed with the T80-South telescope, a robotic telescope located at th
Externí odkaz:
http://arxiv.org/abs/2407.20701
While large language models (LLMs) are extremely capable at text generation, their outputs are still distinguishable from human-authored text. We explore this separation across many metrics over text, many sampling techniques, many types of text data
Externí odkaz:
http://arxiv.org/abs/2401.15476
Very-high energy (GeV-TeV) gamma rays in the universe suggest the presence of an accelerator in the source. Neutrinos and gamma rays are intriguing astrophysical messengers. Multi-messenger particle emission produced by interactions of cosmic rays wi
Externí odkaz:
http://arxiv.org/abs/2312.02389
Mutation validation (MV) is a recently proposed approach for model selection, garnering significant interest due to its unique characteristics and potential benefits compared to the widely used cross-validation (CV) method. In this study, we empirica
Externí odkaz:
http://arxiv.org/abs/2311.14079
Recently, work in NLP has shifted to few-shot (in-context) learning, with large language models (LLMs) performing well across a range of tasks. However, while fairness evaluations have become a standard for supervised methods, little is known about t
Externí odkaz:
http://arxiv.org/abs/2311.08472
Autor:
Sasse, Leonard, Nicolaisen-Sobesky, Eliana, Dukart, Juergen, Eickhoff, Simon B., Götz, Michael, Hamdan, Sami, Komeyer, Vera, Kulkarni, Abhijit, Lahnakoski, Juha, Love, Bradley C., Raimondo, Federico, Patil, Kaustubh R.
Machine learning (ML) provides powerful tools for predictive modeling. ML's popularity stems from the promise of sample-level prediction with applications across a variety of fields from physics and marketing to healthcare. However, if not properly i
Externí odkaz:
http://arxiv.org/abs/2311.04179