SOTAVerified

Memorization

Papers

Showing 661670 of 1088 papers

TitleStatusHype
Progress measures for grokking via mechanistic interpretabilityCode1
ODIM: Outlier Detection via Likelihood of Under-Fitted Generative ModelsCode0
Holistic Label Correction for Noisy Multi-Label ClassificationCode0
Prototypical Mixing and Retrieval-Based Refinement for Label Noise-Resistant Image RetrievalCode0
OT-Filter: An Optimal Transport Filter for Learning With Noisy Labels0
DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and CorrectionCode1
A Mathematical Framework for Learning Probability Distributions0
Execution-Based Evaluation for Open-Domain Code GenerationCode1
When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric MemoriesCode1
ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language ModelsCode1
Show:102550
← PrevPage 67 of 109Next →

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