Abstract
Managing and retrieving complex legal information poses significant challenges, such as handling vast, interconnected legal texts efficiently and ensuring precise interpretation based on context, jurisdiction, and precedents. This paper addresses a critical gap in legal information retrieval systems by introducing an integrated knowledge graph-based approach combined with agent-driven decision making, with Tamil language support as an accessibility feature for regional users. Our comprehensive analysis of existing literature reveals that while current approaches address isolated aspects of the problem, none provides a holistic dynamic solution. Our novel framework introduces two primary contributions: (1) a hierarchical knowledge graph schema that enables structured legal reasoning through multi-layered entity relationships, and (2) adaptive agent reasoning capabilities that dynamically navigate complex legal knowledge structures for contextually relevant responses. The system architecture integrates these core innovations with context-aware graph-based retrieval-augmented generation (RAG) for precise retrieval and incorporates Tamil language processing to enhance accessibility for regional users. Additionally, our approach demonstrates the significance of intent identification fine-tuning, which improves query understanding precision by 23% compared to baseline approaches. Experimental results demonstrate significant improvements in retrieval accuracy and query comprehension compared to traditional keyword-based approaches. Our hierarchical knowledge graph achieved a modularity score of 0.646 using Louvain community detection, while our LangGraph agent attained ROUGE-1/2/L scores of 0.467/0.311/0.508 for single-document tasks. For more complex multi-document retrieval, the ReAct Agent achieved impressive scores of 0.592/0.432/0.512, with high semantic similarity scores of 0.831 and 0.893. The proposed system offers a scalable solution that leverages structured knowledge representation and adaptive reasoning to navigate complex legal relationships, with Tamil language support providing enhanced accessibility for regional users in the Indian legal domain.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data Availability
The datasets analyzed during this study are based on publicly available documents from the Indian Constitution, which can be accessed online. Additional datasets generated during this study are available from the corresponding author upon reasonable request.
References
Beck H, Balog K (2018) Utilizing Knowledge Graphs for Text-Centric Information Retrieval. In: Proceedings of the 41st international ACM SIGIR conference on research & development in information retrieval. ACM, pp 1071–1074
Cai Y, Guo Z, Pei Y et al (2024) SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation. arXiv preprint
Dan J, Hu W, Wang Y (2023) Enhancing legal judgment summarization with integrated semantic and structural information. Artif Intell Law 31(4):1165–1189. https://doi.org/10.1007/s10506-023-09352-1
Dietz L, Kotov A, Meij E (2018) Utilizing Knowledge Graphs for Text-Centric Information Retrieval. In: Proceedings of the 41st international ACM SIGIR conference on research & development in information retrieval
Explosion (2024) spaCy: Industrial-Strength Natural Language Processing. Explosion
Ghosh S (2024) Human Centered AI for Indian Legal Text Analytics. https://doi.org/10.48550/arXiv.2403.10944
Gupta R, Sharma S, Kumar A (2023) Continuous sign language recognition using isolated signs data and deep transfer learning. Ambient Intell Human Comput 14:1531–1542
Hugging Face (2022) Hugging Face Documentation. Hugging Face
Jain S (2022) Constructing a Knowledge Graph from Indian Legal Domain Corpus. CEUR Workshop Proceedings
Janev V, Graux D, Jabeen H et al (2020) Knowledge Graphs and Big Data Processing. Springer. https://doi.org/10.1007/978-3-030-53199-7
Jaradeh MY, Singh K, Stocker M et al (2023) Information Extraction Pipelines for Knowledge Graphs. Know Inf Syst
Le HH (2023) Intelligent Retrieval System on Legal Documents. In: Intelligent information and database systems: 15th Asian conference. https://doi.org/10.1007/978-981-99-5834-4_8
Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Zettlemoyer L (2020) Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv Neural Inf Process Syst 33(2020):9459–9474
Li L, Bi Z, Ye H et al (2021) Text-guided Legal Knowledge Graph Reasoning. arXiv preprint. https://doi.org/10.48550/arXiv.2104.02284
Li B, Deng S, Hong H et al (2025) CoLE: A collaborative legal expert prompting framework for large language models in law. Knowl-Based Syst 113052
Litiana T (2023) Towards LLM-Based Semantic Analysis of Historical Legal Documents. CEUR Workshop Proceedings
Liu B, Yan R, Cai H et al (2022) Query Generation and Buffer Mechanism: Towards a Better Conversational Agent for Legal Case Retrieval. Inf Process Manag 59(5):103051. https://doi.org/10.1016/j.ipm.2022.103051
Manning CD, Raghavan P, Schütze H (2009) An Introduction to Information Retrieval. Cambridge University Press
Naik V, Barot H, Chaudhari A et al (2023) An Effective Search Algorithm for Analyzing and Extracting Indian Legal Judgments Using NER and Document Summarization. In: 2023 7th International conference on computing, communication, control and automation (ICCUBEA). https://doi.org/10.1109/iccubea58933.2023.10392253
Neo4j (2024) Neo4j Documentation. Neo4j
Oliveira F, Parente de Oliveira JM (2023) A RDF-based graph to representing and searching parts of legal documents. Artif Intell Law 31(4):667–695
Oliveira V, Nogueira G, Marcacini R (2024) Combining prompt-based language models and weak supervision for labeling named entity recognition on legal documents. Artif Intell Law 32(1):27–52
Sampath K, Thenmozhi D (2022) PReLCaP: Precedence Retrieval from Legal Documents Using Catch Phrases. Neural Process Lett 54(5):3873–3891. https://doi.org/10.1007/11063-022-10791-z
Sansone C, Sperlí G (2022) Legal Information Retrieval Systems: State-of-the-Art and Open Issues. Inf Syst 106:101967. https://doi.org/10.1016/j.is.2021.101967
Sha Y, Feng Y, He M et al (2023) Retrieval-Augmented Knowledge Graph Reasoning for Commonsense Question Answering. Mathematics
Sheetal S (2022) Knowledge Graph-Based Thematic Similarity for Indian Legal Judgement Documents Using Rhetorical Roles. In: Proceedings of the 19th international conference on natural language processing (ICON)
Singhal A (2012) Introducing the knowledge graph: things, not strings. Official Google Blog 5.16(2012):3
Sivakumar N, Valli S, Santhi G et al (2023) Pooraa-Agri KG: An Agricultural Knowledge Graph-Based Simplified Multilingual Query System. Expert Syst 40(10). https://doi.org/10.1111/exsy.13434
Sovrano F, Palmirani M, Pistone V (2024) DiscoLQA: zero-shot discourse-based legal question answering on European Legislation. Artif Intell Law 32(1):1–25
Tuggener D (2020) LEDGAR: A Large-Scale Dataset for Legal Document Classification. In: Proceedings of the 12th language resources and evaluation conference (LREC 2020), pp 1238–1247
Vargas-Solar G, Alves MHF, Forst ALM (2023) From Text to Knowledge with Graphs: modelling, querying and exploiting textual content. arXiv preprint. https://doi.org/10.48550/arXiv.2310.06122
Wang X, Gao C, Cao J et al (2018) ALTAS: An Intelligent Text Analysis System Based on Knowledge Graphs. In: Web and Big Data (APWeb-WAIM 2018). Springer, pp 466–470
Zhang C, Li Y, Du N et al (2020) Few-shot knowledge graph completion. Proceed AAAI Conference Artif Intell 34(03):3041–3048
Zhang Y, Li X, Wang X (2022) KGTuner: Efficient Hyper-parameter Tuning for Knowledge Graph Learning. In: Proceedings of the 2022 conference on empirical methods in natural language processing (EMNLP)
Zhou X, Li B, Zheng R et al (2024) Unlocking authentic judicial reasoning: A Template-Based Legal Information Generation framework for judicial views. Knowl-Based Syst 301:112232
Zhu J, Wu J, Liu J (2023) Semantic matching based legal information retrieval system for COVID-19 pandemic. Artif Intell Law 31(3):397–426. https://doi.org/10.1007/s10506-023-09339-y
Funding
No funding was received for conducting this research.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, methodology development, data collection, inspection and analysis were performed by all authors. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflicts of Interest
The authors declare that they have no conflicts of interest relevant to the content of this article.
Informed Consent
There were no individual participants in this study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Thenmozhi, D., AG, M.V. & M, N.S. Hierarchical knowledge graph based legal information retrieval from multiple documents using intelligent agents. Artif Intell Law (2025). https://doi.org/10.1007/s10506-025-09491-5
Received:
Accepted:
Published:
Version of record:
DOI: https://doi.org/10.1007/s10506-025-09491-5