SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 226–250 of 1088 papers

TitleStatusHype
Bidirectional deep-readout echo state networksCode0
Demystifying Verbatim Memorization in Large Language ModelsCode0
ModelPred: A Framework for Predicting Trained Model from Training DataCode0
DeMem: Privacy-Enhanced Robust Adversarial Learning via De-MemorizationCode0
An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and CalibrationCode0
LLMs and Memorization: On Quality and Specificity of Copyright ComplianceCode0
Memorization and Knowledge Injection in Gated LLMsCode0
Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge EditingCode0
Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative TrainingCode0
Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Distant SupervisionCode0
Leveraging Unlabeled Data to Track MemorizationCode0
Data Watermarking for Sequential Recommender SystemsCode0
LiDAR-based localization using universal encoding and memory-aware regressionCode0
Dataset distillation for memorized data: Soft labels can leak held-out teacher knowledgeCode0
Data Origin Inference in Machine LearningCode0
KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from ServerCode0
Data Factors for Better Compositional GeneralizationCode0
Iterative Graph AlignmentCode0
Benchmarking Abstract and Reasoning Abilities Through A Theoretical PerspectiveCode0
Adaptive Sample Selection for Robust Learning under Label NoiseCode0
Jogging the Memory of Unlearned LLMs Through Targeted Relearning AttacksCode0
Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNsCode0
Data Contamination: From Memorization to ExploitationCode0
Introducing Orthogonal Constraint in Structural ProbesCode0
Analyzing Memorization in Large Language Models through the Lens of Model AttributionCode0
Show:102550
← PrevPage 10 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