SOTAVerified

Memorization

Papers

Showing 551575 of 1088 papers

TitleStatusHype
Least Squares Maximum and Weighted Generalization-Memorization Machines0
Response: Emergent analogical reasoning in large language modelsCode0
Quantifying and Analyzing Entity-level Memorization in Large Language Models0
Large language models converge toward human-like concept organization0
Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin MemoryCode0
Continuous Reinforcement Learning-based Dynamic Difficulty Adjustment in a Visual Working Memory Game0
A Probabilistic Fluctuation based Membership Inference Attack for Diffusion ModelsCode0
Smoothness Similarity Regularization for Few-Shot GAN Adaptation0
MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain ConversationCode1
U-Turn Diffusion0
LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following0
SimplyRetrieve: A Private and Lightweight Retrieval-Centric Generative AI ToolCode2
3D-EX : A Unified Dataset of Definitions and Dictionary ExamplesCode0
Excitatory/Inhibitory Balance Emerges as a Key Factor for RBN Performance, Overriding Attractor Dynamics0
Training Data Protection with Compositional Diffusion Models0
Arithmetic with Language Models: from Memorization to Computation0
Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processes0
Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?Code0
Image Synthesis under Limited Data: A Survey and TaxonomyCode1
Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?0
Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models0
Distribution Shift Matters for Knowledge Distillation with Webly Collected Images0
Long-Tail Theory under Gaussian MixturesCode0
What can we learn from Data Leakage and Unlearning for Law?0
Can Neural Network Memorization Be Localized?Code1
Show:102550
← PrevPage 23 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