SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 626–650 of 1088 papers

TitleStatusHype
Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?—0
Fuse to Forget: Bias Reduction and Selective Memorization through Model FusionCode0
Minimum Description Length Hopfield NetworksCode0
Data Factors for Better Compositional GeneralizationCode0
Preserving Privacy in GANs Against Membership Inference Attack—0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of NetworksCode0
The statistical thermodynamics of generative diffusion models: Phase transitions, symmetry breaking and critical instability—0
Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding—0
SoK: Memorization in General-Purpose Large Language Models—0
MoPe: Model Perturbation-based Privacy Attacks on Language Models—0
Implications of Annotation Artifacts in Edge Probing Test DatasetsCode0
Copyright Violations and Large Language ModelsCode0
ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks—0
Training Dynamics of Deep Network Linear Regions—0
Unintended Memorization in Large ASR Models, and How to Mitigate It—0
Generation or Replication: Auscultating Audio Latent Diffusion Models—0
Combating Label Noise With A General Surrogate Model For Sample Selection—0
On the Over-Memorization During Natural, Robust and Catastrophic OverfittingCode0
Why Train More? Effective and Efficient Membership Inference via Memorization—0
Exploring Memorization in Fine-tuned Language Models—0
What do larger image classifiers memorise?—0
Grokking as Compression: A Nonlinear Complexity Perspective—0
Probing Large Language Models from A Human Behavioral Perspective—0
Scaling Laws for Associative Memories—0
Show:102550
← PrevPage 26 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