HTLM (prefix 0.1%)

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 GenerationonWebNLG Full
BLEU· uses extra data· 2021-07-14
56.3
best: 62.27 (Control Prefixes (A1, A2, T5-large))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955

Natural Language Processing1 result

Data-to-Text GenerationonWebNLG Full
BLEU· uses extra data· 2021-07-14
56.3
best: 62.27 (Control Prefixes (A1, A2, T5-large))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955