Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Kim, Hazel"'
Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel approach to detecting model hallucination through systematic analysis of
Externí odkaz:
http://arxiv.org/abs/2412.10246
Autor:
Kim, Hazel
Rationales behind answers not only explain model decisions but boost language models to reason well on complex reasoning tasks. However, obtaining impeccable rationales is often impossible. Besides, it is non-trivial to estimate the degree to which t
Externí odkaz:
http://arxiv.org/abs/2402.14337
Solving math word problems depends on how to articulate the problems, the lens through which models view human linguistic expressions. Real-world settings count on such a method even more due to the diverse practices of the same mathematical operatio
Externí odkaz:
http://arxiv.org/abs/2311.01036
Self-training provides an effective means of using an extremely small amount of labeled data to create pseudo-labels for unlabeled data. Many state-of-the-art self-training approaches hinge on different regularization methods to prevent overfitting a
Externí odkaz:
http://arxiv.org/abs/2202.02566
Data augmentation has been an important ingredient for boosting performances of learned models. Prior data augmentation methods for few-shot text classification have led to great performance boosts. However, they have not been designed to capture the
Externí odkaz:
http://arxiv.org/abs/2112.11916
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:10894-10902
Data augmentation has been an important ingredient for boosting performances of learned models. Prior data augmentation methods for few-shot text classification have led to great performance boosts. However, they have not been designed to capture the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee0c0d1c64c08c3ed92791aff8a18021
https://doi.org/10.1609/aaai.v36i10.21336
https://doi.org/10.1609/aaai.v36i10.21336
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Kimberly D Neri, Mark Kevin P Devanadera, Kenshi Watanabe, Reuel M Bennett, Kim Hazel V Arafiles, Tsunehiro Aki, Gina R Dedeles
Publikováno v:
Letters in Applied Microbiology. 76
Mangroves create an ecological environment for a diverse assemblage of organisms, including marine and mangrove oomycetes. Halophytophthora spp., in particular, are isolated from fallen senescent mangrove leaves. Studies reported on Philippines oomyc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::794319fc600ce2670f05ca7069ab29a3
https://doi.org/10.1093/lambio/ovad022
https://doi.org/10.1093/lambio/ovad022
Autor:
Yoshiko Okamura, Risa Higashi, Kenshi Watanabe, Yukihiko Matsumura, Kim Hazel V. Arafiles, Takahisa Tajima, Tsunehiro Aki, Keisuke Matsuyama, Yutaka Nakashimada
Publikováno v:
Journal of Oleo Science. 67:571-578
The marine eukaryotic microheterotroph thraustochytrid genus Aurantiochytrium is a known producer of polyunsaturated fatty acids, carotenoids, and squalene. We previously constructed a lipid fermentation system for Aurantiochytrium sp. strains using
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8752d3fa67de53014485d48161c4441
https://doi.org/10.5650/jos.ess17230
https://doi.org/10.5650/jos.ess17230
Autor:
Reuel M. Bennett, Kim Hazel V. Arafiles, Niño Andree Louis E. Caguimbal, Tsunehiro Aki, Gina R. Dedeles, Kenshi Watanabe, Mark Kevin P. Devanadera
Publikováno v:
Letters in applied microbiology. 69(3)
Studies on marine-sourced fatty acids have gathered significant interest recently as an important component of aquaculture feeds and of biofuel production. Of the organisms capable of producing fatty acids, marine oomycetes are promising model organi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7b2e8c5cb4347c64d9b1458b1b39d494
https://pubmed.ncbi.nlm.nih.gov/31295355
https://pubmed.ncbi.nlm.nih.gov/31295355