SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 1088 papers

TitleStatusHype
Continual Memorization of Factoids in Large Language ModelsCode1
Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian StructureCode1
DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of PlasticityCode1
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of HeuristicsCode1
Scalability of memorization-based machine unlearningCode1
Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context ModelsCode1
Mitigating Memorization In Language ModelsCode1
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and MethodCode1
FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text CompressionCode1
MEOW: MEMOry Supervised LLM Unlearning Via Inverted FactsCode1
CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?Code1
Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMsCode1
MemBench: Memorized Image Trigger Prompt Dataset for Diffusion ModelsCode1
Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy ReasoningCode1
Advancing Cross-domain Discriminability in Continual Learning of Vision-Language ModelsCode1
Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge UtilizationCode1
Sonnet or Not, Bot? Poetry Evaluation for Large Models and DatasetsCode1
SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)Code1
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted PhenomenonCode1
AlleNoise: large-scale text classification benchmark dataset with real-world label noiseCode1
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language ModelsCode1
Can LLM Graph Reasoning Generalize beyond Pattern Memorization?Code1
Data Contamination Can Cross Language BarriersCode1
How Do Large Language Models Acquire Factual Knowledge During Pretraining?Code1
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion ModelsCode1
LlamaCare: A Large Medical Language Model for Enhancing Healthcare Knowledge SharingCode1
PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant PerturbationsCode1
Large Scale Knowledge WashingCode1
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood DiscrepancyCode1
Rethinking Graph Backdoor Attacks: A Distribution-Preserving PerspectiveCode1
MemLLM: Finetuning LLMs to Use An Explicit Read-Write MemoryCode1
Offset Unlearning for Large Language ModelsCode1
Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language ModelsCode1
Localizing Paragraph Memorization in Language ModelsCode1
A Unified Framework for Model EditingCode1
Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization CorrelationsCode1
Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross AttentionCode1
Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact GuidanceCode1
Beyond Memorization: The Challenge of Random Memory Access in Language ModelsCode1
Elephants Never Forget: Testing Language Models for Memorization of Tabular DataCode1
Quantifying Contamination in Evaluating Code Generation Capabilities of Language ModelsCode1
Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language ModelsCode1
Copyright Traps for Large Language ModelsCode1
The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward PassesCode1
Erasing Undesirable Influence in Diffusion ModelsCode1
RoleEval: A Bilingual Role Evaluation Benchmark for Large Language ModelsCode1
Negative Pre-aware for Noisy Cross-modal MatchingCode1
Sparse Low-rank Adaptation of Pre-trained Language ModelsCode1
Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language ModelsCode1
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language ModelsCode1
Show:102550
← PrevPage 2 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