SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 776–800 of 1088 papers

TitleStatusHype
Detecting Memorization in Large Language Models—0
Detecting Memorization in ReLU Networks—0
Detecting Unintended Memorization in Language-Model-Fused ASR—0
Detection and Measurement of Syntactic Templates in Generated Text—0
Differential learning kinetics govern the transition from memorization to generalization during in-context learning—0
Differentially Private Fine-Tuning of Diffusion Models—0
Diffusing DeBias: a Recipe for Turning a Bug into a Feature—0
Diffusion Soup: Model Merging for Text-to-Image Diffusion Models—0
Discovering Forbidden Topics in Language Models—0
Distributed Associative Memory Network with Association Reinforcing Loss—0
Distributed Skellam Mechanism: a Novel Approach to Federated Learning with Differential Privacy—0
Distribution Shift Matters for Knowledge Distillation with Webly Collected Images—0
DNN or k-NN: That is the Generalize vs. Memorize Question—0
Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods—0
Does Learning Require Memorization? A Short Tale about a Long Tail—0
Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?—0
Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach—0
Do Larger Language Models Imply Better Reasoning? A Pretraining Scaling Law for Reasoning—0
Do RNN States Encode Abstract Phonological Processes?—0
Do RNN States Encode Abstract Phonological Alternations?—0
Do sequence-to-sequence VAEs learn global features of sentences?—0
Do We Need to Penalize Variance of Losses for Learning with Label Noise?—0
Do We Train on Test Data? Purging CIFAR of Near-Duplicates—0
Downsampling leads to Image Memorization in Convolutional Autoencoders—0
Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splitting—0
Show:102550
← PrevPage 32 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