
Sign up to save your podcasts
Or


EURUS, a suite of large language models, excels in reasoning tasks, surpassing GPT-3.5 Turbo. Its success is attributed to ULTRAINTERACT, a dataset enhancing preference learning for complex reasoning.
https://arxiv.org/abs//2404.02078
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
By Igor Melnyk5
33 ratings
EURUS, a suite of large language models, excels in reasoning tasks, surpassing GPT-3.5 Turbo. Its success is attributed to ULTRAINTERACT, a dataset enhancing preference learning for complex reasoning.
https://arxiv.org/abs//2404.02078
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers

956 Listeners

1,942 Listeners

437 Listeners

111,970 Listeners

9,971 Listeners

5,512 Listeners

211 Listeners

49 Listeners

92 Listeners

473 Listeners