SOTAVerified

Memorization

Papers

Showing 251275 of 1088 papers

TitleStatusHype
LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training DataCode0
Minimum Description Length Hopfield NetworksCode0
Dataset distillation for memorized data: Soft labels can leak held-out teacher knowledgeCode0
Data Origin Inference in Machine LearningCode0
Leveraging Unlabeled Data to Track MemorizationCode0
LiDAR-based localization using universal encoding and memory-aware regressionCode0
Data Factors for Better Compositional GeneralizationCode0
Benchmarking Abstract and Reasoning Abilities Through A Theoretical PerspectiveCode0
Adaptive Sample Selection for Robust Learning under Label NoiseCode0
Leave-one-out Distinguishability in Machine LearningCode0
Data Contamination: From Memorization to ExploitationCode0
Analyzing Memorization in Large Language Models through the Lens of Model AttributionCode0
DAS3H: Modeling Student Learning and Forgetting for Optimally Scheduling Distributed Practice of SkillsCode0
ModelPred: A Framework for Predicting Trained Model from Training DataCode0
CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental LearningCode0
Learning to Infer Program SketchesCode0
Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context LearningCode0
Automatic Classification of Attributes in German Adjective-Noun PhrasesCode0
An Inversion-based Measure of Memorization for Diffusion ModelsCode0
Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNsCode0
Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation SpaceCode0
Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled MembershipsCode0
Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion ModelsCode0
Copyright Violations and Large Language ModelsCode0
Iterative Graph AlignmentCode0
Show:102550
← PrevPage 11 of 44Next →

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