This study investigates transformers' inconsistent performance on two-hop questions, revealing that capacity scaling and generalization affect their ability to learn and answer these complex queries effectively.
https://arxiv.org/abs//2502.03490
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
Information
- Show
- FrequencyUpdated Daily
- PublishedFebruary 7, 2025 at 4:51 AM UTC
- Length8 min
- RatingClean