LlamBERT: Large-scale low-cost data annotation in NLP
Open paper
Benchmark
Model
Rank
Results
sentiment-analysis-on-imdb
RoBERTa-large with LlamBERT
#1
Accuracy: 96.68
sentiment-analysis-on-imdb
RoBERTa-large
#2
Accuracy: 96.54
sentiment-analysis-on-imdb
Llama-2-70b-chat (0-shot)
#16
Accuracy: 95.39
Rank counts only results with a code link.