@misc{keisha_all_2025,
 abstract = {Retrieval-Augmented Generation (RAG) mitigates hallucinations by grounding large language model outputs in cited sources, a capability that is especially critical in the legal domain. We present an end-to-end RAG pipeline that revisits and extends the LegalBenchRAG baseline with 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 (improving Recall@K by 30-95\% and Precision@K by \$\sim\$2.5\$\times\$ for \$K\textgreater4\$) 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 or outperform 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.},
 annote = {Comment: submitted to NLLP 2025 Workshop},
 author = {Keisha, Figarri and Singh, Prince and Pallavi and Fernandes, Dion and Manivannan, Aravindh and Wicaksono, Ilham and Ahmad, Faisal},
 doi = {10.48550/arXiv.2508.13107},
 file = {Preprint PDF:/Users/figarrikeisha/Zotero/storage/DFYA8SVT/Keisha et al. - 2025 - All for law and law for all Adaptive RAG Pipeline for Legal Research.pdf:application/pdf;Snapshot:/Users/figarrikeisha/Zotero/storage/6TPY2PGU/2508.html:text/html},
 keywords = {Computer Science - Computation and Language, Computer Science - Information Retrieval},
 month = {August},
 note = {arXiv:2508.13107 [cs]},
 publisher = {arXiv},
 shorttitle = {All for law and law for all},
 title = {All for law and law for all: Adaptive RAG Pipeline for Legal Research},
 url = {http://arxiv.org/abs/2508.13107},
 urldate = {2025-08-20},
 year = {2025}
}