Go offline with the Player FM app!
Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
Manage episode 429596591 series 3524393
This paper explores how increasing datastore size enhances retrieval-based language models' performance, demonstrating that smaller models with large datastores outperform larger models in knowledge-intensive tasks.
https://arxiv.org/abs//2407.12854
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
1533 episodes
Manage episode 429596591 series 3524393
This paper explores how increasing datastore size enhances retrieval-based language models' performance, demonstrating that smaller models with large datastores outperform larger models in knowledge-intensive tasks.
https://arxiv.org/abs//2407.12854
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
1533 episodes
All episodes
×Welcome to 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.