Parameter-efficient fine-tuning (LoRA family)
LAP
Superseded baseline#109 of 1,113 most-superseded
Superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 2 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating LAP. Values are copied from the source paper's tables — verify against the cited paper.
BLRB (N=10) beats LAP
3.77 vs 8.70
ECE · [OBQA (In-Dist.)]
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language ModelsiLoRA beats LAP
0.0980 vs 0.2031
ECE · [IBD diagnosis overall]
iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome DiagnosisBLRB (N=0) beats LAP
82.73 vs 82.12
ACC · [OBQA (In-Dist.)]
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for 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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.