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

arXiv: https://arxiv.org/abs/2609.39189 · HTML: https://mlsanity.com/paper/2609.39189/

## 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 (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence](https://mlsanity.com/paper/2004.12158/) (2020)
- [JEC-QA: A Legal-Domain Question Answering Dataset](https://mlsanity.com/paper/1911.12011/) (2019)
- [Large-Scale Multi-Label Text Classification on EU Legislation](https://mlsanity.com/paper/1906.02192/) (2019)
- [Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives](https://mlsanity.com/paper/1905.10847/) (2019)
- [A Statutory Article Retrieval Dataset in French](https://mlsanity.com/paper/2108.11792/) (2021)
- [A Replication Study of Dense Passage Retriever](https://mlsanity.com/paper/2104.05740/) (2021)
- [ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation](https://mlsanity.com/paper/2205.06457/) (2022)
- [BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese](https://mlsanity.com/paper/2109.09701/) (2021)
- [MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.06713/) (2025)
- [Dual Co-Matching Network for Multi-choice Reading Comprehension](https://mlsanity.com/paper/1901.09381/) (2019)
- [Multi-style Generative Reading Comprehension](https://mlsanity.com/paper/1901.02262/) (2019)
- [A Deep Cascade Model for Multi-Document Reading Comprehension](https://mlsanity.com/paper/1811.11374/) (2018)
- [ViDeBERTa: A powerful pre-trained language model for Vietnamese](https://mlsanity.com/paper/2301.10439/) (2023)
- [S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension](https://mlsanity.com/paper/1706.04815/) (2017)
- [CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering](https://mlsanity.com/paper/2011.00519/) (2020)
- [VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering](https://mlsanity.com/paper/2507.19995/) (2025)
- [Measuring the Groundedness of Legal Question-Answering Systems](https://mlsanity.com/paper/2410.08764/) (2024)

## 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.