LLaMA-13B+CFG (zero-shot)

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Adversarial1 result

Text GenerationonSciQ
Accuracy· 2023-06-30
95.1
best: 96.6 (LLaMA-65B+CFG (zero-shot))
Stay on topic with Classifier-Free Guidance arXiv:2306.17806

Medical1 result

Language ModellingonLAMBADA
Accuracy· 2023-06-30
82.2
best: 89.7 (PaLM-540B (Few-Shot))
Stay on topic with Classifier-Free Guidance arXiv:2306.17806