作者位次 #3/5ACL 2026Poster· Natural Language Processing
W eight L o RA : Keep Only Necessary Adapters
Andrey Veprikov · Vladimir Solodkin · Zyl Alexander · Andrey V. Savchenko · Aleksandr Beznosikov
摘要
The widespread utilization of language models in modern applications is inconceivable without Parameter-Efficient Fine-Tuning techniques, such as low-rank adaptation ( LoRA ), which adds trainable adapters to selected layers. Although LoRA may obtain accurate solutions, it requires significant me...