Parameter-efficient fine-tuning (LoRA family)

LIFT

LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks

Superseded baseline#735 of 1,113 most-superseded · first seen Jun 14, 2022

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites LIFT as a baseline.

Although effective, these methods require substantial storage equivalent to the full model since all parameters are being updated. Furthermore, these approaches do not deeply explore joint use with PEFT and have employed relatively simple selection strategies, limiting their performance.
Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.