SOTAVerified

Memorization

Papers

Showing 5160 of 1088 papers

TitleStatusHype
Data Contamination Can Cross Language BarriersCode1
Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language ModelsCode1
Mitigating Memorization of Noisy Labels via Regularization between RepresentationsCode1
DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature DistributionsCode1
Advancing Cross-domain Discriminability in Continual Learning of Vision-Language ModelsCode1
An Empirical Study of Memorization in NLPCode1
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language ModelsCode1
Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-LearningCode1
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of HeuristicsCode1
Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy AnnotationsCode1
Show:102550
← PrevPage 6 of 109Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PaLM-540B (few-shot, k=5)Accuracy95.4Unverified
2Gopher-280B (few-shot, k=5)Accuracy80Unverified
3PaLM-62B (few-shot, k=5)Accuracy77.7Unverified