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 →

2 results 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
Research · Efficiency & systems
Combining model compression techniques can collapse small language models
Compression Technique Interactions in Small Language Models: A Factorial Ablation Study
A systematic study of 72 compression configurations shows that INT8 quantization is lossless, while NF4 with pruning causes total failure, and LoRA fine-tuning recovers most quality without a teacher model.
WikiText-2: 920.56 perplexity (as reported)
3 Nov 2026Amazon Web Services