All for law and law for all: Adaptive RAG Pipeline for Legal Research
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915488249937920 |
|---|---|
| author | Keisha, Figarri Singh, Prince Pallavi Fernandes, Dion Manivannan, Aravindh Wicaksono, Ilham Ahmad, Faisal Rim, Wiem Ben |
| author_facet | Keisha, Figarri Singh, Prince Pallavi Fernandes, Dion Manivannan, Aravindh Wicaksono, Ilham Ahmad, Faisal Rim, Wiem Ben |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13107 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | All for law and law for all: Adaptive RAG Pipeline for Legal Research Keisha, Figarri Singh, Prince Pallavi Fernandes, Dion Manivannan, Aravindh Wicaksono, Ilham Ahmad, Faisal Rim, Wiem Ben Computation and Language Information Retrieval F.2.2; H.3.3; I.2.7 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. |
| title | All for law and law for all: Adaptive RAG Pipeline for Legal Research |
| topic | Computation and Language Information Retrieval F.2.2; H.3.3; I.2.7 |
| url | https://arxiv.org/abs/2508.13107 |