The paper explores post-training methods for large language models to enhance both output diversity and quality in creative writing, achieving human-like diversity with minimal quality loss.

https://arxiv.org/abs//2503.17126

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