arXiv:2611.21823v1 Announce Type: new Abstract: Evaluating retrieval-augmented generation (RAG) systems in Persian law remains challenging because benchmarks lack realism, grounding, and coverage of legal reasoning. Existing resources are either synthetically generated from statutory texts, lacking natural information needs, or derived from informal legal question--answer sources without explicit linkage to authoritative legal documents, making them unsuitable for rigorous evaluation of grounded legal reasoning. To address this gap, we introduce TUSI-Bench, a structured Persian legal benchmark designed for the evaluation of RAG-based systems. TUSI-Bench is built upon a multi-layered legal knowledge framework containing 7,261 legal articles and integrating codified statutes, legal commentaries, doctrinal writings, and Supreme Court unification rulings. We also construct a legal knowledge graph linking articles and concepts for structure-aware retrieval. Based on this foundation, TUSI-Bench provides two complementary evaluation tasks: (i) TUSI-QA, an open-ended question answering benchmark containing 1,999 questions that requires grounded responses with explicit legal citations, and (ii) TUSI-Bar, a multiple-choice benchmark containing approximately 500 four-option questions derived from Iranian Bar examination questions. Furthermore, we propose a graph-based retrieval baseline that leverages relational structure within the legal knowledge graph. Experimental results demonstrate that incorporating graph-based relations improves retrieval recall by up to 8 percentage points compared to standard baselines, highlighting the importance of structured legal representations for RAG systems. The proposed benchmark provides a standardized resource for evaluating grounded legal reasoning in Persian and enables future research on structured legal intelligence.
TUSI: A Citation-Grounded Graph-Based Benchmark
Researchers introduced TUSI-Bench, a Persian legal benchmark for evaluating retrieval-augmented generation systems, built on a multi-layered framework of 7,261 legal articles spanning codified statutes, legal commentaries, doctrinal writings and Supreme Court unification rulings. TUSI-Bench comprises TUSI-QA, 1,999 open-ended questions requiring grounded answers with explicit legal citations, and TUSI-Bar, roughly 500 four-option multiple-choice questions drawn from Iranian Bar examination questions, alongside a legal knowledge graph linking articles and concepts. A proposed graph-based retrieval baseline that exploits the knowledge graph's relational structure improved retrieval recall by up to 8 percentage points over standard baselines, according to the arXiv paper 2611.21823v1.
Link legal articles and concepts in a knowledge graph and retrieve over its relational structure; the source measured up to 8 percentage points higher recall than standard baselines.
more in playbook: Retrieval and RAGRun your AI side-project on zahid.host
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.