SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 901–925 of 1088 papers

TitleStatusHype
On the Robustness of Monte Carlo Dropout Trained with Noisy Labels—0
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models—0
On the privacy-utility trade-off in differentially private hierarchical text classificationCode0
Parsimonious Inference—0
Membership Inference Attacks are Easier on Difficult ProblemsCode0
Robust Generalization and Safe Query-Specialization in Counterfactual Learning to RankCode0
Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance EvaluationCode0
Learning to Combat Noisy Labels via Classification Margins—0
Meta-Regularization by Enforcing Mutual-ExclusivenessCode0
PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network—0
Investigating Memorization of Conspiracy Theories in Text GenerationCode0
The Unreasonable Effectiveness of the Class-reversed Sampling in Tail Sample Memorization—0
ME-MOMENTUM: EXTRACTING HARD CONFIDENT EXAMPLES FROM NOISILY LABELED DATA—0
Distributed Associative Memory Network with Association Reinforcing Loss—0
Catching the Long Tail in Deep Neural Networks—0
A Large-scale Study on Training Sample Memorization in Generative Modeling—0
Making Coherence Out of Nothing At All: Measuring Evolution of Gradient Alignment—0
Robust early-learning: Hindering the memorization of noisy labels—0
Continual Memory: Can We Reason After Long-Term Memorization?—0
How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?Code0
Introducing Orthogonal Constraint in Structural ProbesCode0
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization—0
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks—0
Perceptron Theory Can Predict the Accuracy of Neural Networks—0
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?Code0
Show:102550
← PrevPage 37 of 44Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PaLM-540B (few-shot, k=5)Accuracy95.4—Unverified
2Gopher-280B (few-shot, k=5)Accuracy80—Unverified
3PaLM-62B (few-shot, k=5)Accuracy77.7—Unverified