What question did this study set out to answer?

The research aims to improve the accuracy of question-answering for Indonesian legal documents using Retrieval-Augmented Generation.

March 29, 2026

LawRAG: Indonesian legal document retrieval-augmented generation with specialized chunking and reranking strategies

Key Points

The research aims to improve the accuracy of question-answering for Indonesian legal documents using Retrieval-Augmented Generation.
Employs a Retrieval-Augmented Generation design tailored for new Indonesian law documents.
Incorporates a specialized chunking methodology based on document titles, articles, and paragraphs.
Utilizes a reranker model to refine the retrieval process.
The proposed method significantly surpasses the accuracy of traditional sequential chunking methods.
Completeness of sentences during the retrieval phase greatly influences RAG response accuracy.
Stronger connections between article titles and contents enhance context-awareness.

Abstract

Purpose Enhancing Question-Answering accuracy on new law documents by using Retrieval-Augmented Generation (RAG)-Large Language Models . Design/methodology/approach The proposed method is built on a RAG design for Indonesian new law documents, incorporating a specific data chunking method and a reranker model. Findings The proposed method, which segments legal data by focusing on the document title, article, and paragraph, outperforms the sequential chunking method in terms of accuracy. Originality/value This research demonstrates that the completeness of a sentence in the data set used during the retrieval phase of RAG significantly affects the accuracy of RAG responses. This is particularly true for legal documents, which are closely tied to the titles of articles and the wording of each legal provision. The relationship between the article titles and the content enhances the context-awareness of each data chunking process.

Mark Helpful

Bookmark

Relay