# Legal and financial RAG

Area: [Retrieval-augmented generation](https://mlsanity.com/rag/index.md). HTML: https://mlsanity.com/rag/legal-and-financial-rag/

## Key facts

- Legal and financial RAG: 130 papers on arXiv since 2023 (data through 14 Oct 2026).
- 21 of its 130 mapped papers (16%) cite “LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain” (2024, arXiv 2408.10343).
- 6 of its 130 mapped papers (5%) cite “Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models” (2023, arXiv 2309.17050).
- 7 new papers 17 Sep–14 Oct.

## Most cited here

- [LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain](https://mlsanity.com/paper/2408.10343/) (2024), cited by 21 papers here
- [Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2309.17050/) (2023), cited by 6 papers here
- [CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering](https://mlsanity.com/paper/2404.04302/) (2024), cited by 6 papers here
- [A Reasoning-Focused Legal Retrieval Benchmark](https://mlsanity.com/paper/2505.03970/) (2025), cited by 6 papers here
- [HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction](https://mlsanity.com/paper/2408.04948/) (2024), cited by 5 papers here
- [FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.15800/) (2025), cited by 5 papers here
- [HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications](https://mlsanity.com/paper/2409.09046/) (2024), cited by 4 papers here
- [Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge](https://mlsanity.com/paper/2411.16732/) (2024), cited by 4 papers here
- [FinSage: A Multi-aspect RAG System for Financial Filings Question Answering](https://mlsanity.com/paper/2504.14493/) (2025), cited by 4 papers here
- [AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework](https://mlsanity.com/paper/2403.12582/) (2024), cited by 3 papers here

## New (17 Sep–14 Oct)

- [Legal-R1: Agentic Retrieval for Evidence-Based Legal Reasoning](https://mlsanity.com/paper/2610.18611/) (2026-10-13)
- [Token-Budgeted Escalation for Financial Document QA: Cost Is Predictable, Benefit Is the Bottleneck](https://mlsanity.com/paper/2610.07760/) (2026-10-06)
- [LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence](https://mlsanity.com/paper/2610.01027/) (2026-10-01)
- [Grounded Revision vs. Prior Injection: Probing Retrieval-Augmented Patent Claim Amendment](https://mlsanity.com/paper/2609.36550/) (2026-09-29)
- [LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting](https://mlsanity.com/paper/2609.30943/) (2026-09-25)
- [Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.30009/) (2026-09-24)
- [Efficient LLM Distillation for Bangladesh Legal Context: A Smartphone-Compatible Retrieval-Augmented Generation Model](https://mlsanity.com/paper/2609.24177/) (2026-09-21)