mlsanityData to 14 Oct 2026

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

arXiv 2609.39189 ↗First posted 30 Sep 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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. We introduce ViLegalExpert, a large-scale benchmark constructed from authentic citizen--lawyer consultations, containing over 172K questions across 34 legal domains, together with professional answers and expert-verified legal evidence. ViLegalExpert supports legal information retrieval, extractive QA, and abstractive QA. Experiments with representative retrieval methods and language models reveal substantial challenges in evidence retrieval and grounded answer generation. While pretrained models perform strongly on QA, hybrid retrieval achieves the best retrieval performance. These results demonstrate the difficulty of mapping naturally expressed legal questions to authoritative provisions and establish ViLegalExpert as a challenging benchmark for reliable Vietnamese Legal AI.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 30 Sep 2026.

Builds on

25 of 40 references.

References · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  3. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  4. 2019How multilingual is Multilingual BERT?cited by 645
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  6. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  7. 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
  8. 2020PhoBERT: Pre-trained language models for Vietnamesecited by 149
  9. 2020How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligencecited by 129
  10. 2019JEC-QA: A Legal-Domain Question Answering Datasetcited by 116
  11. 2019Large-Scale Multi-Label Text Classification on EU Legislationcited by 104
  12. 2019Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narrativescited by 59
13 more
  1. 2021A Statutory Article Retrieval Dataset in Frenchcited by 40
  2. 2021A Replication Study of Dense Passage Retrievercited by 37
  3. 2022ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generationcited by 37
  4. 2021BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamesecited by 34
  5. 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
  6. 2019Dual Co-Matching Network for Multi-choice Reading Comprehensioncited by 26
  7. 2019Multi-style Generative Reading Comprehensioncited by 14
  8. 2018A Deep Cascade Model for Multi-Document Reading Comprehensioncited by 11
  9. 2023ViDeBERTa: A powerful pre-trained language model for Vietnamesecited by 11
  10. 2017S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehensioncited by 6
  11. 2020CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answeringcited by 6
  12. 2025VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answeringcited by 4
  13. 2024Measuring the Groundedness of Legal Question-Answering Systemscited by 1

Built on by

Not cited yet.