# Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documents

arXiv: https://arxiv.org/abs/2603.11772 · HTML: https://mlsanity.com/paper/2603.11772/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023)
- [SaulLM-7B: A pioneering Large Language Model for Law](https://mlsanity.com/paper/2403.03883/) (2024)
- [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023)
- [UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation](https://mlsanity.com/paper/2303.08518/) (2023)
- [RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation](https://mlsanity.com/paper/2403.05313/) (2024)
- [Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In](https://mlsanity.com/paper/2305.17331/) (2023)
- [Lawyer LLaMA Technical Report](https://mlsanity.com/paper/2305.15062/) (2023)
- [CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2401.17043/) (2024)
- [Financial Report Chunking for Effective Retrieval Augmented Generation](https://mlsanity.com/paper/2402.05131/) (2024)
- [Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking](https://mlsanity.com/paper/2310.13243/) (2023)
- [MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering](https://mlsanity.com/paper/2404.05590/) (2024)
- [Better Call GPT, Comparing Large Language Models Against Lawyers](https://mlsanity.com/paper/2401.16212/) (2024)
- [HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses](https://mlsanity.com/paper/2312.15883/) (2023)
- [Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study](https://mlsanity.com/paper/2404.11792/) (2024)

## Built on by (most cited first, 2 of 2)

- [ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance](https://mlsanity.com/paper/2608.19974/) (2026)
- [Annotated Surrogate Retrieval for Polish Statutory Law](https://mlsanity.com/paper/2608.30929/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has emerged as a promising technology for legal document consultation, yet its application in Chinese legal scenarios faces two key limitations: existing benchmarks lack specialized support for joint retriever-generator evaluation, and mainstream RAG systems often fail to accommodate the structured nature of legal provisions. To address these gaps, this study advances two core contributions: First, we constructed the Legal-DC benchmark dataset, comprising 480 legal documents (covering areas such as market regulation and contract management) and 2,475 refined question-answer pairs, each annotated with clause-level references, filling the gap for specialized evaluation resources in Chinese legal RAG. Second, we propose the LegRAG framework, which integrates legal adaptive indexing (clause-boundary segmentation) with a dual-path self-reflection mechanism to ensure clause integrity while enhancing answer accuracy. Third, we introduce automated evaluation methods for large language models to meet the high-reliability demands of legal retrieval scenarios. LegRAG outperforms existing state-of-the-art methods by 1.3% to 5.6% across key evaluation metrics. This research provides a specialized benchmark, practical framework, and empirical insights to advance the development of Chinese legal RAG systems. Our code and data are available at https://github.com/legal-dc/Legal-DC.