SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 501–550 of 1088 papers

TitleStatusHype
Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval—0
Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward LayersCode0
Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment—0
Extracting Training Data from Document-Based VQA Models—0
PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding—0
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization—0
Towards More Realistic Extraction Attacks: An Adversarial PerspectiveCode0
Detection and Measurement of Syntactic Templates in Generated Text—0
Enhancing Data Privacy in Large Language Models through Private Association Editing—0
Generative artificial intelligence in ophthalmology: multimodal retinal images for the diagnosis of Alzheimer's disease with convolutional neural networks—0
modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models—0
Learning with Noisy Ground Truth: From 2D Classification to 3D Reconstruction—0
Scaling Laws for Fact Memorization of Large Language Models—0
Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models—0
Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning—0
Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models—0
Jogging the Memory of Unlearned LLMs Through Targeted Relearning AttacksCode0
Unmasking the Veil: An Investigation into Concept Ablation for Privacy and Copyright Protection in ImagesCode0
Extracting Training Data from Unconditional Diffusion Models—0
Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3Code0
Measuring memorization in RLHF for code completion—0
Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning—0
Automating Pharmacovigilance Evidence Generation: Using Large Language Models to Produce Context-Aware SQL—0
Between Randomness and Arbitrariness: Some Lessons for Reliable Machine Learning at Scale—0
Exploring Fact Memorization and Style Imitation in LLMs Using QLoRA: An Experimental Study and Quality Assessment Methods—0
Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens—0
Diffusion Soup: Model Merging for Text-to-Image Diffusion Models—0
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-TeachingCode0
Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research—0
Memorization in deep learning: A survey—0
What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions—0
Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping—0
Differentially Private Fine-Tuning of Diffusion Models—0
Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted—0
A Machine Learning-Based Framework for Assessing Cryptographic Indistinguishability of Lightweight Block Ciphers—0
MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter SelectionCode0
LLMs and Memorization: On Quality and Specificity of Copyright ComplianceCode0
How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks—0
When does compositional structure yield compositional generalization? A kernel theoryCode0
Unsupervised Meta-Learning via In-Context Learning—0
The Mosaic Memory of Large Language ModelsCode0
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension—0
Next-token prediction capacity: general upper bounds and a lower bound for transformersCode0
Asymptotic theory of in-context learning by linear attentionCode0
FINED: Feed Instance-Wise Information Need with Essential and Disentangled Parametric Knowledge from the Past—0
Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs—0
A Multi-Perspective Analysis of Memorization in Large Language Models—0
Learnable Privacy Neurons Localization in Language Models—0
Generalized Holographic Reduced Representations—0
Dynamic Loss Decay based Robust Oriented Object Detection on Remote Sensing Images with Noisy Labels—0
Show:102550
← PrevPage 11 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