All for law and law for all: Adaptive RAG Pipeline for Legal Research

TL;DR

This paper presents an advanced RAG pipeline tailored for legal research, integrating context-aware query translation, open-source retrieval, and comprehensive evaluation to produce more faithful and relevant legal answers.

Contribution

It introduces a novel end-to-end RAG pipeline with targeted enhancements for legal research, emphasizing cost-efficiency, task-awareness, and reproducibility.

Findings

Open-source retrieval strategies outperform proprietary methods in retrieval quality.

Custom legal-grounded prompts improve answer faithfulness and relevance.

The pipeline achieves competitive performance with cost-effective components.

Abstract

Retrieval-Augmented Generation (RAG) has transformed how we approach text generation tasks by grounding Large Language Model (LLM) outputs in retrieved knowledge. This capability is especially critical in the legal domain. In this work, we introduce a novel end-to-end RAG pipeline that improves upon previous baselines using three targeted enhancements: (i) a context-aware query translator that disentangles document references from natural-language questions and adapts retrieval depth and response style based on expertise and specificity, (ii) open-source retrieval strategies using SBERT and GTE embeddings that achieve substantial performance gains while remaining cost-efficient, and (iii) a comprehensive evaluation and generation framework that combines RAGAS, BERTScore-F1, and ROUGE-Recall to assess semantic alignment and faithfulness across models and prompt designs. Our results show that carefully designed open-source pipelines can rival proprietary approaches in retrieval quality, while a custom legal-grounded prompt consistently produces more faithful and contextually relevant answers than baseline prompting. Taken together, these contributions demonstrate the potential of task-aware, component-level tuning to deliver legally grounded, reproducible, and cost-effective RAG systems for legal research assistance.