SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 751–775 of 1088 papers

TitleStatusHype
Markov chain Hebbian learning algorithm with ternary synaptic units—0
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations—0
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence—0
MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Models—0
Measures of Information Reflect Memorization Patterns—0
Measuring Forgetting of Memorized Training Examples—0
Measuring Memorization Effect in Word-Level Neural Networks Probing—0
Measuring memorization in RLHF for code completion—0
Measuring memorization through probabilistic discoverable extraction—0
Measuring Non-Adversarial Reproduction of Training Data in Large Language Models—0
MediaEval 2018: Predicting Media Memorability Task—0
Mehler's Formula, Branching Process, and Compositional Kernels of Deep Neural Networks—0
Membership Inference Attacks on Sequence Models—0
MemGEN: Memory is All You Need—0
MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs—0
ME-MOMENTUM: EXTRACTING HARD CONFIDENT EXAMPLES FROM NOISILY LABELED DATA—0
Memorization: A Close Look at Books—0
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization—0
Memorization Capacity of Neural Networks with Conditional Computation—0
Memorization-Compression Cycles Improve Generalization—0
Memorization in deep learning: A survey—0
Memorization in In-Context Learning—0
Memorization in Overparameterized Autoencoders—0
Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis—0
Memorization or Reasoning? Exploring the Idiom Understanding of LLMs—0
Show:102550
← PrevPage 31 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