Crossing Linguistic Horizons

Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models

Few-Shot Toxicity Detection Leaderboard

Models UiT-ViCTSD UiT-ViHSD
AC F1 AR ECE A@10 AC F1 AR ECE A@10
URA-LLaMa 70B 0.44 ± 0.01 0.27 ± 0.01 0.75 ± 0.01 0.52 ± 0.01 0.37 ± 0.02 0.17 ± 0.00 0.15 ± 0.00 0.64 ± 0.01 0.57 ± 0.00 0.27 ± 0.02
URA-LLaMa 13B 0.44 ± 0.01 0.30 ± 0.05 0.67 ± 0.01 0.33 ± 0.01 0.41 ± 0.03 0.26 ± 0.01 0.16 ± 0.00 0.61 ± 0.01 0.42 ± 0.01 0.21 ± 0.02
URA-LLaMa 7B 0.43 ± 0.01 0.40 ± 0.01 0.60 ± 0.01 0.29 ± 0.01 0.71 ± 0.02 0.16 ± 0.00 0.10 ± 0.00 0.67 ± 0.01 0.32 ± 0.00 0.28 ± 0.02
LLaMa-2 13B 0.28 ± 0.01 0.19 ± 0.00 0.67 ± 0.01 0.52 ± 0.01 0.63 ± 0.03 0.17 ± 0.00 0.11 ± 0.00 0.62 ± 0.01 0.58 ± 0.00 0.44 ± 0.02
LLaMa-2 7B 0.16 ± 0.01 0.12 ± 0.01 0.61 ± 0.01 0.66 ± 0.01 0.08 ± 0.02 0.01 ± 0.00 0.01 ± 0.00 0.56 ± 0.01 0.71 ± 0.00 0.01 ± 0.02
Vietcuna 7B 0.08 ± 0.00 0.10 ± 0.01 0.50 ± 0.00 0.42 ± 0.00 0.08 ± 0.03 0.61 ± 0.01 0.21 ± 0.00 0.50 ± 0.00 0.28 ± 0.01 0.61 ± 0.02
MixSUra 8x7B 0.70 ± - 0.39 ± - - ± - 0.29 ± - 0.80 ± - 0.58 ± - 0.31 ± - 0.68 ± - 0.30 ± - 0.93 ± -
GPT-3.5 0.63 ± 0.02 0.54 ± 0.02 - 0.13 ± 0.02 0.63 ± 0.05 0.63 ± 0.01 0.47 ± 0.01 - 0.29 ± 0.01 0.63 ± 0.02
GPT-4 0.89 ± 0.00 0.71 ± 0.01 - 0.39 ± 0.00 0.89 ± 0.03 0.77 ± 0.01 0.57 ± 0.01 - 0.44 ± 0.01 0.77 ± 0.02