Lune

ACL Findings2025

GRAF: Graph Retrieval Augmented by Facts for Romanian Legal Multi-Choice Question Answering

Cristian-George Craciun, Razvan-Alexandru Smadu, Dumitru-Clementin Cercel, Mihaela-Claudia Cercel

Abstract

Pre-trained language models have shown remarkable performance in recent years, setting a new paradigm for natural language processing (NLP) research. The legal domain has received some attention from the NLP community, in part due to its textual nature. Question answering (QA) systems represent some of the tasks in this domain. This work explores the legal multiple-choice QA (MCQA) for Romanian. The contribution of this work is multifold. We introduce JuRO, the first openly available Romanian legal MCQA dataset, comprising 10,836 questions from three examinations. Along with this dataset, we introduce CROL, an organized corpus of laws comprising a total of 93 distinct documents with their modifications over 763 time spans, which we used for information retrieval techniques in this work. Additionally, we construct Law-RoG, the first graph of legal knowledge for the Romanian language, derived from the aforementioned corpus. Lastly, we propose a novel approach for MCQA, namely Graph Retrieval Augmented by Facts (GRAF), which achieves competitive results with generally accepted state-of-the-art methods and even exceeds them in most settings.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • LoRA: Low-Rank Adaptation of Large Language Models cites Language Models are Few-Shot Learners
  • Finetuned Language Models are Zero-Shot Learners cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on8

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  3. Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
  4. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTOmar Khattab, Matei ZahariaSIGIR 2020 · 1,246 citations
  5. JEC-QA: A Legal-Domain Question Answering DatasetHaoxi Zhong, Chaojun Xiao, Cunchao Tu, Tianyang Zhang et al.AAAI 2020 · 212 citations

Related papers

  1. RoQLlama: A Lightweight Romanian Adapted Language ModelGeorge-Andrei Dima, Andrei-Marius Avram, Cristian-George Craciun, Dumitru-Clementin CercelEMNLP Findings 2024 · 5 citations
  2. Enhancing Distractor Generation for Multiple-Choice Questions with Retrieval Augmented Pretraining and Knowledge Graph IntegrationHan-Cheng Yu, Yu-An Shih, Kin-Man Law, Kai-Yu Hsieh et al.ACL Findings 2024 · 18 citations
  3. From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal ConsultationMingfei Lu, Yi Zhang, Mengjia Wu, Yue FengACL 2026 · 2 citations
  4. The birth of Romanian BERTStefan Daniel Dumitrescu, Andrei-Marius Avram, Sampo PyysaloEMNLP Findings 2020 · 3 citations
  5. H-LegalKI: A Hierarchical Legal Knowledge Integration Framework for Legal Community Question AnsweringYue Jiang, Ziyu Guan, Jie Zhao, Wei Zhao et al.EMNLP Findings 2024 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines