SOTAVerified

MMLU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 340 papers

TitleStatusHype
Learning What Matters: Probabilistic Task Selection via Mutual Information for Model Finetuning—0
Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMsCode0
Lizard: An Efficient Linearization Framework for Large Language Models—0
Integrating External Tools with Large Language Models to Improve Accuracy—0
Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen SubstrateCode0
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong GainsCode1
any4: Learned 4-bit Numeric Representation for LLMsCode2
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training—0
Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode RepresentationsCode0
Multi-lingual Functional Evaluation for Large Language Models—0
Show:102550
← PrevPage 1 of 34Next →
All datasetsSIOP 2020/2021MMLU-ProVCTK

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HybridBeam+SI-SDRi13.3—Unverified