Retrieval-Augmented Generation for Indonesian Criminal Law Information Using the LLaMA Model

Abstract

Law is a set of rules that regulate boundaries of behavior
within society, is coercive in nature, and imposes sanctions
on violators. One of its branches is criminal law, which
focuses on violations of norms with the threat of sanctions.
However, the legal system often provides excessive
discretion to the judiciary, making legal outcomes difficult to
predict and potentially disadvantageous, especially for
individuals who lack legal understanding or cannot afford
legal representation. This disparity poses a significant
challenge to legal systems in many countries. In this study,
we demonstrate that artificial intelligence (AI) based on
Retrieval-Augmented Generation (RAG) can serve as an
innovative solution to support a more equitable enforcement
of the law. This technology integrates information retrieval
and data-driven text generation to help the public understand
their rights, access valid legal information, and obtain
relevant legal guidance. Based on the implementation and
testing of a criminal law chatbot using the LLaMA language
model, questions, generated answers, and the relevance of
the chatbot's responses were evaluated. Out of ten tested
questions, eight received relevant responses, while two were
deemed irrelevant. Additionally, the chatbot's capability to
retrieve legal documents based on user-provided prompts
was assessed. Of ten input prompts, the chatbot successfully
identified eight relevant documents, achieving a hit rate of
80%. Thus, the application of RAG in this legal chatbot can
provide an innovative solution to support law enforcement.
In the future, the use of AI in legal systems has the potential
to reduce information disparities, enhance transparency in
legal processes, and create a more efficient and accessible
legal system for all.