Gå offline med appen Player FM !
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Manage episode 431845373 series 3524393
This paper explores scaling inference compute by increasing sample generation, demonstrating improved problem-solving coverage and performance across tasks, while highlighting challenges in selecting correct solutions from multiple samples.
https://arxiv.org/abs//2407.21787
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
--- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/support
1645 episoder
Manage episode 431845373 series 3524393
This paper explores scaling inference compute by increasing sample generation, demonstrating improved problem-solving coverage and performance across tasks, while highlighting challenges in selecting correct solutions from multiple samples.
https://arxiv.org/abs//2407.21787
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
--- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/support
1645 episoder
Alle episoder
×Velkommen til Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.