JurisGraph Insight Engine 1.0v: A Legal Question Answering System Based on Large Language Models and Knowledge Graphs

Haiguang Zhang
Proceedings of the 17th Asian Conference on Machine Learning, PMLR 304:255-270, 2025.

Abstract

The extraction and effective utilization of judicial data remains a major challenge in the legal domain. There is a growing mismatch between the public’s demand for accessible legal services and the high cost and complexity of legal consultations, which also affects the efficiency of legal professionals when handling case inquiries. Traditional keyword-based search methods lack professionalism, interpretability, and scalability. In this paper, we propose JurisGraph Insight Engine 1.0v, an intelligent legal question-answering (QA) system that integrates large language models (LLMs) and domain-specific knowledge graphs. We first construct a comprehensive Criminal Law Knowledge Graph (CLKG) containing 483 types of criminal offenses, and develop two unified heterogeneous subgraphs for theft and drug-related cases. Then, we fine-tune a domain-specific legal LLM, LawM, using a curated corpus of over 280,000 Chinese legal records covering multiple legal NLP tasks. Finally, we design and implement a QA system that leverages both the knowledge graph and LawM to deliver accurate and interpretable answers to legal questions. Experimental results show that our system achieves 95% accuracy, effectively lowering the barrier to legal knowledge access for the general public while improving decision efficiency for legal practitioners.

Cite this Paper

BibTeX
@InProceedings{pmlr-v304-zhang25a, title = {JurisGraph Insight Engine 1.0v: A Legal Question Answering System Based on Large Language Models and Knowledge Graphs}, author = {Zhang, Haiguang}, booktitle = {Proceedings of the 17th Asian Conference on Machine Learning}, pages = {255--270}, year = {2025}, editor = {Lee, Hung-yi and Liu, Tongliang}, volume = {304}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v304/main/assets/zhang25a/zhang25a.pdf}, url = {https://proceedings.mlr.press/v304/zhang25a.html}, abstract = {The extraction and effective utilization of judicial data remains a major challenge in the legal domain. There is a growing mismatch between the public’s demand for accessible legal services and the high cost and complexity of legal consultations, which also affects the efficiency of legal professionals when handling case inquiries. Traditional keyword-based search methods lack professionalism, interpretability, and scalability. In this paper, we propose JurisGraph Insight Engine 1.0v, an intelligent legal question-answering (QA) system that integrates large language models (LLMs) and domain-specific knowledge graphs. We first construct a comprehensive Criminal Law Knowledge Graph (CLKG) containing 483 types of criminal offenses, and develop two unified heterogeneous subgraphs for theft and drug-related cases. Then, we fine-tune a domain-specific legal LLM, LawM, using a curated corpus of over 280,000 Chinese legal records covering multiple legal NLP tasks. Finally, we design and implement a QA system that leverages both the knowledge graph and LawM to deliver accurate and interpretable answers to legal questions. Experimental results show that our system achieves 95% accuracy, effectively lowering the barrier to legal knowledge access for the general public while improving decision efficiency for legal practitioners.} }
Endnote
%0 Conference Paper %T JurisGraph Insight Engine 1.0v: A Legal Question Answering System Based on Large Language Models and Knowledge Graphs %A Haiguang Zhang %B Proceedings of the 17th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Hung-yi Lee %E Tongliang Liu %F pmlr-v304-zhang25a %I PMLR %P 255--270 %U https://proceedings.mlr.press/v304/zhang25a.html %V 304 %X The extraction and effective utilization of judicial data remains a major challenge in the legal domain. There is a growing mismatch between the public’s demand for accessible legal services and the high cost and complexity of legal consultations, which also affects the efficiency of legal professionals when handling case inquiries. Traditional keyword-based search methods lack professionalism, interpretability, and scalability. In this paper, we propose JurisGraph Insight Engine 1.0v, an intelligent legal question-answering (QA) system that integrates large language models (LLMs) and domain-specific knowledge graphs. We first construct a comprehensive Criminal Law Knowledge Graph (CLKG) containing 483 types of criminal offenses, and develop two unified heterogeneous subgraphs for theft and drug-related cases. Then, we fine-tune a domain-specific legal LLM, LawM, using a curated corpus of over 280,000 Chinese legal records covering multiple legal NLP tasks. Finally, we design and implement a QA system that leverages both the knowledge graph and LawM to deliver accurate and interpretable answers to legal questions. Experimental results show that our system achieves 95% accuracy, effectively lowering the barrier to legal knowledge access for the general public while improving decision efficiency for legal practitioners.
APA
Zhang, H.. (2025). JurisGraph Insight Engine 1.0v: A Legal Question Answering System Based on Large Language Models and Knowledge Graphs. Proceedings of the 17th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 304:255-270 Available from https://proceedings.mlr.press/v304/zhang25a.html.

Related Material