Crossing Linguistic Horizons

Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models

Few-Shot Sentiment Analysis Leaderboard

Models VLSP 2016 UiT-VSFC
AC↑ F1↑ AR↑ ECE↓ A@10↑ AC↑ F1↑ AR↑ ECE↓ A@10↑
URA-LLaMa 70B 0.66 ± 0.01 0.49 ± 0.01 0.72 ± 0.01 0.13 ± 0.01 0.77 ± 0.04 0.75 ± 0.01 0.48 ± 0.01 0.81 ± 0.01 0.16 ± 0.01 0.71 ± 0.02
URA-LLaMa 13B 0.59 ± 0.01 0.57 ± 0.01 0.67 ± 0.01 0.09 ± 0.01 0.82 ± 0.04 0.74 ± 0.01 0.52 ± 0.08 0.83 ± 0.01 0.10 ± 0.01 0.87 ± 0.02
URA-LLaMa 7B 0.57 ± 0.02 0.42 ± 0.05 0.69 ± 0.02 0.07 ± 0.02 0.77 ± 0.04 0.72 ± 0.01 0.43 ± 0.01 0.78 ± 0.01 0.13 ± 0.01 0.95 ± 0.03
LLaMa-2 13B 0.51 ± 0.01 0.41 ± 0.06 0.66 ± 0.01 0.32 ± 0.02 0.80 ± 0.04 0.63 ± 0.01 0.46 ± 0.07 0.71 ± 0.01 0.13 ± 0.01 0.88 ± 0.02
LLaMa-2 7B 0.45 ± 0.01 0.32 ± 0.01 0.59 ± 0.01 0.26 ± 0.02 0.50 ± 0.05 0.50 ± 0.01 0.34 ± 0.01 0.69 ± 0.01 0.23 ± 0.01 0.62 ± 0.03
Vietcuna 7B 0.04 ± 0.01 0.05 ± 0.01 0.45 ± 0.01 0.71 ± 0.01 0.05 ± 0.02 0.03 ± 0.00 0.03 ± 0.00 0.53 ± 0.01 0.50 ± 0.00 0.01 ± 0.00
MixSUra 8x7B 0.62 ± - 0.63 ± - 0.59 ± - 0.30 ± - 0.59 ± - 0.74 ± - 0.46 ± - 0.63 ± - 0.23 ± - 0.655 ± -
GPT-3.5 0.65 ± 0.01 0.59 ± 0.1 - 0.32 ± 0.01 0.65 ± 0.05 0.86 ± 0.01 0.73 ± 0.01 - 0.52 ± 0.01 0.86 ± 0.02
GPT-4 0.75 ± 0.01 0.74 ± 0.01 - 0.41 ± 0.01 0.74 ± 0.04 0.85 ± 0.01 0.59 ± 0.09 - 0.52 ± 0.01 0.85 ± 0.02