Crossing Linguistic Horizons

Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models

Robustness-Aware Sentiment Analysis Leaderboard

Models VLSP 2016 UiT-VSFC
AC↑ F1↑ AR↑ ECE↓ A@10↑ AC↑ F1↑ AR↑ ECE↓ A@10↑
URA-LLaMa 70B 0.63 ± 0.01 0.48 ± 0.01 0.60 ± 0.01 0.09 ± 0.01 0.83 ± 0.04 0.71 ± 0.01 0.45 ± 0.01 0.80 ± 0.01 0.08 ± 0.01 0.99 ± 0.01
URA-LLaMa 13B 0.55 ± 0.02 0.52 ± 0.02 0.59 ± 0.01 0.06 ± 0.01 0.74 ± 0.05 0.72 ± 0.01 0.44 ± 0.05 0.77 ± 0.01 0.18 ± 0.01 0.77 ± 0.02
URA-LLaMa 7B 0.52 ± 0.02 0.36 ± 0.03 0.59 ± 0.01 0.07 ± 0.01 0.66 ± 0.05 0.73 ± 0.01 0.41 ± 0.01 0.71 ± 0.01 0.16 ± 0.01 0.87 ± 0.02
LLaMa-2 13B 0.46 ± 0.02 0.30 ± 0.01 0.55 ± 0.01 0.39 ± 0.02 0.70 ± 0.05 0.66 ± 0.01 0.40 ± 0.01 0.63 ± 0.01 0.11 ± 0.01 0.89 ± 0.02
LLaMa-2 7B 0.45 ± 0.02 0.36 ± 0.01 0.54 ± 0.01 0.20 ± 0.02 0.51 ± 0.05 0.51 ± 0.01 0.33 ± 0.01 0.65 ± 0.01 0.15 ± 0.01 0.80 ± 0.02
Vietcuna 7B 0.44 ± 0.02 0.27 ± 0.01 0.51 ± 0.01 0.23 ± 0.02 0.53 ± 0.05 0.49 ± 0.01 0.25 ± 0.03 0.46 ± 0.01 0.33 ± 0.01 0.34 ± 0.03
MixSUra 8x7B 0.59 ± - 0.59 ± - 0.55 ± - 0.34 ± - 0.52 ± - 0.69 ± - 0.44 ± - 0.61 ± - 0.29 ± - 0.66 ± -
GPT-3.5 0.64 ± 0.01 0.60 ± 0.01 - 0.31 ± 0.01 0.54 ± 0.05 0.86 ± 0.01 0.71 ± 0.01 - 0.53 ± 0.01 0.86 ± 0.02
GPT-4 0.74 ± 0.00 0.73 ± 0.00 - 0.41 ± 0.00 0.71 ± 0.00 0.83 ± 0.00 0.70 ± 0.00 - 0.50 ± 0.00 0.85 ± 0.00