Parameter-efficient fine-tuning (LoRA family)

Sequential adapters

Superseded baseline#957 of 1,113 most-superseded

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 Sequential adapters as a baseline.

Sequential adapters incur roughly 4–6% slowdown relative to full fine-tuning, which compounds in multi-task settings
Understanding and Guiding Layer Placement 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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.