Leveraging Retrieval-Augmented Generation to Support Legal Question Answering: Evidence from Indonesian Human Trafficking Court Decisions
JOIV : International Journal on Informatics Visualization · 31.07.2026 · 10 (4) · 1674
DOI: 10.62527/joiv.10.4.4760 ↗Kurz gefasst
Fachartikel in der Zeitschrift JOIV : International Journal on Informatics Visualization, online erschienen am 31.07.2026. Verfasst von Galih Wasis Wicaksono und 7 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
The exponential growth of court decisions in Indonesia has posed a crucial challenge for legal practitioners in obtaining relevant information. Conventional search systems fail to capture the in-depth legal context, while Large Language Models (LLMs) are prone to producing hallucinations that can mislead legal reasoning. This study proposes and tests the implementation of Retrieval-Augmented Generation (RAG) to support Legal Question Answering LLM-based Quality Assurance (LQA) to improve factual accuracy. This study used 408 Indonesian court decisions related to criminal cases. Human trafficking data collected and standardized from 143 district courts. The RAG framework is designed in three stages: indexing, search, and incremental generation. We evaluated three Open-source LLM models: Gemma, LLaMA, and Qwen. Three models are also combined with two retrieval methods: BM25 (lexical) and Dense (semantics). Experimental results show that Qwen 3, especially when combined with BM25 RAG, consistently produces the highest overall answer quality across all evaluation metrics (ROUGE and BLEU). The BM25 method is significantly more effective than dense retrieval. Due to the highly standardized nature of court decision documents, Qwen demonstrated peak performance on structured information categories such as “identitas_terdakwa”, achieving a ROUGE-L score of 0.899. The primary contribution of this study is demonstrating that RAG significantly reduces the risk of LLM hallucinations in a legal context. However, error analysis suggests that future improvements should focus on strengthening generation controls to address these issues: unsupported generation and remaining model-rejection behavior.
Zitieren
APA
Wicaksono, G. W., Hidayah, N. P., Aditya, C. S. K., Anwar, M. H. F., Anhari, N. A., Dewa, A. F. P., Fatikasari, H., & Insani, M. A. P. (2026). Leveraging Retrieval-Augmented Generation to Support Legal Question Answering: Evidence from Indonesian Human Trafficking Court Decisions. JOIV : International Journal on Informatics Visualization, 10(4), 1674. https://doi.org/10.62527/joiv.10.4.4760
Vancouver
Wicaksono GW, Hidayah NP, Aditya CSK, Anwar MHF, Anhari NA, Dewa AFP, et al. Leveraging Retrieval-Augmented Generation to Support Legal Question Answering: Evidence from Indonesian Human Trafficking Court Decisions. JOIV : International Journal on Informatics Visualization. 2026;10(4):1674. doi:10.62527/joiv.10.4.4760
BibTeX
@article{Wicaksono2026,
author = {Wicaksono, Galih Wasis and Hidayah, Nur Putri and Aditya, Christian Sri Kusuma and Anwar, Muhammad Hariz Faizul and Anhari, Nizam Avif and Dewa, Andiko Febriyan Praja and Fatikasari, Herlena and Insani, Mutiara Anggun Puspa},
title = {Leveraging Retrieval-Augmented Generation to Support Legal Question Answering: Evidence from Indonesian Human Trafficking Court Decisions},
journal = {JOIV : International Journal on Informatics Visualization},
year = {2026},
volume = {10},
number = {4},
pages = {1674},
doi = {10.62527/joiv.10.4.4760}
}
EUVIMED