Method Drift›Parameter-efficient fine-tuning (LoRA family)
MAP
MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading ComprehensionParameter-efficient fine-tuning (LoRA family) · 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superseded — cited as a baseline and beaten by newer methods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.
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP · ACC [OBQA dataset]
82.8 vs 77.9
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP · ACC [CQA dataset]
79.2 vs 76.2
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP · ACC [ARC-E dataset]
83.7 vs 78.3
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP · ACC [ARC-C dataset]
66.5 vs 57.8
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP · NLL [OBQA dataset]
0.49 vs 0.68
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP · NLL [CQA dataset]
0.59 vs 0.69
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP · NLL [ARC-E dataset]
0.53 vs 0.68
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
MultiSWAG beats MAP · NLL [ARC-C dataset]
0.91 vs 1.14
- Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
Bayesian-LoRA (S=4) beats MAP · ACC [WG-S benchmark, ACC metric]
70.90 vs 68.00
- Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
Bayesian-LoRA (S=4) beats MAP · ECE [WG-S benchmark, ECE metric]
4.90 vs 30.80
- Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
Bayesian-LoRA (S=4) beats MAP · NLL [WG-S benchmark, NLL metric]
0.79 vs 2.75
- Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
Bayesian-LoRA (S=4) beats MAP · ACC [WG-M benchmark, ACC metric]
74.30 vs 73.70
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.