Vietnamese legal datasets for QA, NLI, multiple choice, document detection and revision, plus a legal corpus (VLSP at INLG 2025).
AI & ML interests
Natural Language Processing; Graph Representation Learning; Drug Discovery
Recent Activity
These are datasets used for Vietnamese LLM evaluation
Pretrained Large Language Models based on Gemma built by URA
-
ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-reward_bench
Viewer • Updated • 4.1k • 9 -
ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-winogrande
Viewer • Updated • 9.25k • 9 -
ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-truthful_qa
Viewer • Updated • 2.63k • 15 -
ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-arc_challenge
Viewer • Updated • 3.35k • 9
Vietnamese legal datasets for QA, NLI, multiple choice, document detection and revision, plus a legal corpus (VLSP at INLG 2025).
These are datasets used for Vietnamese LLM evaluation
State-of-the-art MoE Large Language Model for Vietnamese
Pretrained Large Language Models based on Gemma built by URA
First Pretrained LLaMa-2 for Vietnamese
-
ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-reward_bench
Viewer • Updated • 4.1k • 9 -
ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-winogrande
Viewer • Updated • 9.25k • 9 -
ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-truthful_qa
Viewer • Updated • 2.63k • 15 -
ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-arc_challenge
Viewer • Updated • 3.35k • 9