Search

Any time Past 24 hours Past week Past monthSort:Relevance Newest

Benchmark

MMLU

Reported in 43 papers on Zotpaper. The latest, each as the paper states it:

Training language models on false facts they disbelieve causes broader misalignment68.9% accuracy
Language models can learn facts while misjudging what they know0.71 accuracy
Random tweaks suppress leaked personal data as well as targeted fixes61.5% accuracy

MMLU-PRO (25)MMLU-Redux (3)All benchmarks →

1 result for “MMLU”

Research · Language models
AI chatbots fail long tasks due to competing content, not length
Length Is Cheap, Competition Is Not: Attention Predicts Context Rot in Retrieval
Neutral filler costs nothing in retrieval tests, while a few rival statements crash accuracy and attention on the evidence predicts the loss.
MMLU: 51.7% accuracy (as reported)
4 Nov 2026University of California San DiegoCode