作者位次 #4/6ACL 2026Poster· Natural Language Processing
Min- k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
Yuanhao Ding · Meimingwei Li · Esteban Garces Arias · Matthias Aßenmacher · Christian Heumann · Chongsheng Zhang
摘要
The quality of text generated by large language models depends critically on the decoding sampling strategy. While mainstream methods such as Top- k , Top- p , and Min- p achieve a balance between diversity and accuracy through probability-space truncation, they share an inherent limitation: extr...