Crossing Linguistic Horizons

Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models

Robustness-Aware Toxicity Detection Leaderboard

Models UiT-ViCTSD UiT-ViHSD
AC F1 AR ECE A@10 AC F1 AR ECE A@10
URA-LLaMa 70B 0.32 ± 0.00 0.21 ± 0.00 0.72 ± 0.01 0.62 ± 0.00 0.33 ± 0.00 0.14 ± 0.00 0.12 ± 0.00 0.64 ± 0.02 0.61 ± 0.00 0.23 ± 0.00
URA-LLaMa 13B 0.27 ± 0.00 0.26 ± 0.00 0.56 ± 0.00 0.56 ± 0.00 0.12 ± 0.00 0.18 ± 0.00 0.11 ± 0.00 0.57 ± 0.01 0.45 ± 0.00 0.20 ± 0.00
URA-LLaMa 7B 0.22 ± 0.00 0.21 ± 0.00 0.63 ± 0.00 0.39 ± 0.00 0.36 ± 0.00 0.12 ± 0.00 0.07 ± 0.00 0.62 ± 0.00 0.38 ± 0.00 0.19 ± 0.00
LLaMa-2 13B 0.12 ± 0.00 0.11 ± 0.00 0.56 ± 0.01 0.66 ± 0.00 0.12 ± 0.00 0.10 ± 0.00 0.07 ± 0.00 0.59 ± 0.01 0.62 ± 0.00 0.24 ± 0.00
LLaMa-2 7B 0.04 ± 0.00 0.04 ± 0.00 0.62 ± 0.00 0.86 ± 0.00 0.02 ± 0.00 0.01 ± 0.00 0.00 ± 0.00 0.54 ± 0.00 0.79 ± 0.00 0.00 ± 0.00
Vietcuna 7B 0.11 ± 0.00 0.11 ± 0.00 0.54 ± 0.00 0.39 ± 0.00 0.13 ± 0.00 0.09 ± 0.00 0.05 ± 0.00 0.5 ± 0.00 0.24 ± 0.00 0.08 ± 0.00
MixSUra 8x7B 0.72 ± - 0.39 ± - - ± - 0.25 ± - 0.81 ± - 0.66 ± - 0.31 ± - 0.67 ± - 0.21 ± - 0.82 ± -
GPT-3.5 0.51 ± 0.00 0.46 ± 0.00 0.5 ± 0.00 0.01 ± 0.00 0.54 ± 0.00 0.64 ± 0.00 0.47 ± 0.00 - ± - 0.30 ± 0.00 0.63 ± 0.00
GPT-4 0.88 ± 0.00 0.71 ± 0.00 - ± - 0.38 ± 0.00 0.88 ± 0.00 0.78 ± 0.00 0.56 ± 0.00 - ± - 0.44 ± 0.00 0.78 ± 0.00