Zobrazeno 1 - 10
of 152
pro vyhledávání: '"Fonseca, Márcio"'
Large language models (LLMs) often struggle with complex logical reasoning due to logical inconsistencies and the inherent difficulty of such reasoning. We use Lean, a theorem proving framework, to address these challenges. By formalizing logical rea
Externí odkaz:
http://arxiv.org/abs/2403.13312
Autor:
Fonseca, Marcio, Cohen, Shay B.
In this work, we investigate the controllability of large language models (LLMs) on scientific summarization tasks. We identify key stylistic and content coverage factors that characterize different types of summaries such as paper reviews, abstracts
Externí odkaz:
http://arxiv.org/abs/2401.10415
Autor:
Fonseca, Marcio, Cohen, Shay B.
Although large language models (LLMs) exhibit remarkable capacity to leverage in-context demonstrations, it is still unclear to what extent they can learn new concepts or facts from ground-truth labels. To address this question, we examine the capaci
Externí odkaz:
http://arxiv.org/abs/2311.08704
Autor:
Fonseca, Márcio Ribeiro da1 marciof@espm.br, Rocha, Thelma Valéria1 tvrocha@espm.br, Cruz Costa Alves, Antonio Pedro1 apedroa@yahoo.com
Publikováno v:
International Journal on Food System Dynamics. 2024, Vol. 15 Issue 4, p358-375. 18p.
We argue that disentangling content selection from the budget used to cover salient content improves the performance and applicability of abstractive summarizers. Our method, FactorSum, does this disentanglement by factorizing summarization into two
Externí odkaz:
http://arxiv.org/abs/2205.12486
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Fonseca, Marcio
Deep predictive coding networks are neuroscience-inspired unsupervised learning models that learn to predict future sensory states. We build upon the PredNet implementation by Lotter, Kreiman, and Cox (2016) to investigate if predictive coding repres
Externí odkaz:
http://arxiv.org/abs/1907.00441
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Rocha-Filho, Marco Augusto Sobreira, Studart-da-Fonseca-Filho, Marcio Ribeiro, Studart-da-Fonseca, Marina Cavalcanti, Brito da Silva, Harley, Studart-da-Fonseca, Marcio Ribeiro
Publikováno v:
In Interdisciplinary Neurosurgery: Advanced Techniques and Case Management March 2022 27
Autor:
Fonseca, Márcio Ribeiro da
Publikováno v:
Biblioteca Digital de Teses e Dissertações da ESPMEscola Superior de Propaganda e MarketingESPM.
Made available in DSpace on 2016-10-13T14:09:57Z (GMT). No. of bitstreams: 1 Marcio Ribeiro da Fonseca.pdf: 1339481 bytes, checksum: 0bf9307d96cecde1d37406e1c2c5c4e6 (MD5) Previous issue date: 2014-05-26
This study has as its theme the influence
This study has as its theme the influence
Externí odkaz:
http://tede2.espm.br/handle/tede/24