MAP (Parameter-efficient fine-tuning (LoRA family)): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 3 beat it on benchmarks — #65 of 1113 most-superseded. Sub-problem: cluster led by BLoB. Newer alternatives in the same sub-problem include iLoRA, LoRA-VBLL.

Parameter-efficient fine-tuning (LoRA family)

MAP

MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension

Superseded baseline#65 of 1,113 most-superseded · first seen Sep 29, 2020

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 3 beat it on benchmarks

Beaten on benchmarks

Head-to-head results where a newer method reports beating MAP. Values are copied from the source paper's tables — verify against the cited paper.

Bayesian-LoRA (S=4) beats MAP
3.00 vs 24.90
ECE · [WG-M benchmark, ECE metric]
Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP
0.49 vs 0.68
NLL · [OBQA dataset]
Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
iLoRA beats MAP
0.6557 vs 0.6496
F1 (UC) · [IBD diagnosis overall]
iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.