Skip to content
NewA calmer, faster ZeroHour

ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World Consultations

arXiv cs.AI / cs.LG / cs.CLby Dat Tien Nguyen ()1 min read1 · 1 read
AI summary · grok-4.7Summaries by Vani AI

ViLegalExpert benchmarks Vietnamese legal retrieval and QA on 172K real consultation questions.

ViLegalExpert is a Vietnamese legal benchmark built from authentic citizen-lawyer consultations, with more than 172,000 questions across 34 domains, professional answers, and expert-verified legal evidence. It supports information retrieval, extractive question answering, and abstractive question answering. Experiments find pretrained models strong on QA and hybrid retrieval best for retrieval, while mapping naturally worded questions to authoritative provisions remains difficult.

Key facts
  • Over 172,000 questions across 34 legal domains
  • Built from real citizen-lawyer consultations with verified evidence
  • Covers retrieval, extractive QA, and abstractive QA
  • Hybrid retrieval achieved the best retrieval results
  • Grounding natural questions in statutes remains hard
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

Trustworthy Legal AI requires systems that can answer legal questions while grounding their responses in authoritative sources. However, existing Vietnamese legal benchmarks provide limited coverage of real-world legal consultations.

arXiv cs.AI / cs.LG / cs.CL

By Dat Tien Nguyen · arxiv.org

Read the full article at arXiv cs.AI / cs.LG / cs.CL

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.