SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 951–1000 of 1088 papers

TitleStatusHype
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of NetworksCode0
Grokking ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model BehaviorCode0
SIGUA: Forgetting May Make Learning with Noisy Labels More RobustCode0
Grid Long Short-Term MemoryCode0
MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter SelectionCode0
Data Origin Inference in Machine LearningCode0
Investigating Memorization of Conspiracy Theories in Text GenerationCode0
Protecting Copyrighted Material with Unique Identifiers in Large Language Model TrainingCode0
Generalization-Memorization MachinesCode0
Data Factors for Better Compositional GeneralizationCode0
Fuse to Forget: Bias Reduction and Selective Memorization through Model FusionCode0
Fundamental tradeoffs between memorization and robustness in random features and neural tangent regimesCode0
What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structureCode0
Memorization and Generalization in Neural Code Intelligence ModelsCode0
Memorization and Knowledge Injection in Gated LLMsCode0
SoK: Unintended Interactions among Machine Learning Defenses and RisksCode0
Memorization and Regularization in Generative Diffusion ModelsCode0
Memorization Capacity of Multi-Head Attention in TransformersCode0
SolidMark: Evaluating Image Memorization in Generative ModelsCode0
Data Contamination: From Memorization to ExploitationCode0
Memorization-Dilation: Modeling Neural Collapse Under Label NoiseCode0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
Memorization in Attention-only TransformersCode0
Sometimes I am a Tree: Data Drives Unstable Hierarchical GeneralizationCode0
Memorization in Deep Neural Networks: Does the Loss Function matter?Code0
Quantifying Generalization Complexity for Large Language ModelsCode0
Fragments to Facts: Partial-Information Fragment Inference from LLMsCode0
Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge EditingCode0
Memorization in Self-Supervised Learning Improves Downstream GeneralizationCode0
DAS3H: Modeling Student Learning and Forgetting for Optimally Scheduling Distributed Practice of SkillsCode0
Benchmarking Abstract and Reasoning Abilities Through A Theoretical PerspectiveCode0
Span Selection Pre-training for Question AnsweringCode0
Finding Memo: Extractive Memorization in Constrained Sequence Generation TasksCode0
Automatic Classification of Attributes in German Adjective-Noun PhrasesCode0
Quantifying the Corpus Bias Problem in Automatic Music Transcription SystemsCode0
Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance EvaluationCode0
Attributing Culture-Conditioned Generations to Pretraining CorporaCode0
Split and Rephrase: Better Evaluation and Stronger BaselinesCode0
Memorization With Neural Nets: Going Beyond the Worst CaseCode0
Querying Kernel Methods Suffices for Reconstructing their Training DataCode0
CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental LearningCode0
Question Dependent Recurrent Entity Network for Question AnsweringCode0
An Inversion-based Measure of Memorization for Diffusion ModelsCode0
Memory-Modular Classification: Learning to Generalize with Memory ReplacementCode0
Copyright Violations and Large Language ModelsCode0
Split and Rephrase: Better Evaluation and a Stronger BaselineCode0
Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender BiasCode0
The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text MemorizationCode0
Meta-Learning without MemorizationCode0
Meta-Regularization by Enforcing Mutual-ExclusivenessCode0
Show:102550
← PrevPage 20 of 22Next →

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