The paper examines the impact of input length extension on Large Language Models, revealing a notable decrease in reasoning performance at shorter lengths than expected, with insights for future research.

https://arxiv.org/abs//2402.14848

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