LoRATRF inserts a learned cosine-similarity filter and low-rank transformation into LoRA's hidden states, claiming better accuracy with 33.71% fewer parameters, though the reported gains are inconsistent.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Low-Rank Adaptation with Task-Relevant Feature Enhancement for Fine-tuning Language Models
LoRATRF inserts a learned cosine-similarity filter and low-rank transformation into LoRA's hidden states, claiming better accuracy with 33.71% fewer parameters, though the reported gains are inconsistent.