Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Robert Praas"'
Publikováno v:
PeerJ Computer Science, Vol 10, p e1999 (2024)
Emergent chain-of-thought (CoT) reasoning capabilities promise to improve the performance and explainability of large language models (LLMs). However, uncertainties remain about how reasoning strategies formulated for previous model generations gener
Externí odkaz:
https://doaj.org/article/db39e7d1ae9643f99b996443979a9609
Autor:
Simon Ott, Konstantin Hebenstreit, Valentin Liévin, Christoffer Egeberg Hother, Milad Moradi, Maximilian Mayrhauser, Robert Praas, Ole Winther, Matthias Samwald
Publikováno v:
Scientific Data, Vol 10, Iss 1, Pp 1-12 (2023)
Abstract Large language models (LLMs) such as GPT-4 have recently demonstrated impressive results across a wide range of tasks. LLMs are still limited, however, in that they frequently fail at complex reasoning, their reasoning processes are opaque,
Externí odkaz:
https://doaj.org/article/cfd6089d4104413787e743dddb10d8e7
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e032455fe42d3af4f8ac7a48e44808cd
https://doi.org/10.2139/ssrn.4446991
https://doi.org/10.2139/ssrn.4446991