Author(s)

ChenJian Wang, YiMing Li^*

Affiliation(s)

Department of Computing, Imperial College London, London, UK. 

Corresponding Author

YiMing Li

ABSTRACT

This paper proposes a knowledge-driven framework for enhancing legal decision support systems through the integration of Large Language Models. As legal professionals face increasing complexity and volume of information in their practice, traditional LDSS often fall short due to their reliance on rigid algorithms and insufficient adaptability to new legal precedents. The proposed framework emphasizes the systematic organization, representation, and acquisition of legal knowledge, enabling LLMs to provide more accurate and contextually relevant insights. By leveraging the advanced natural language processing capabilities of LLMs, the framework aims to streamline legal research, improve decision-making efficiency, and enhance the overall quality of legal practice. The findings suggest that this integration can significantly benefit legal professionals by allowing them to focus on substantive legal work while addressing ethical considerations associated with AI deployment in law. This paper calls for further collaboration between researchers and practitioners to refine these technologies and ensure their responsible use in the legal domain.

KEYWORDS

Legal decision support systems; Large language models; Knowledge-driven framework

CITE THIS PAPER

ChenJian Wang, YiMing Li. A knowledge-driven framework for enhancing legal decision support with large language models. Multidisciplinary Journal of Engineering and Technology. 2024, 1(2): 10-16. DOI: https://doi.org/10.61784/mjet3014.

REFERENCES

[1] Chen J, Cui Y, Zhang X, Yang J, Zhou M. Temporal Convolutional Network for Carbon Tax Projection: A Data-Driven Approach. Applied Sciences, 2024, 14(20): 9213

[2] Wang X, Wu Y C. Empowering legal justice with AI: A reinforcement learning SAC-VAE framework for advanced legal text summarization. PloS one, 2024, 19(10): e0312623.

[3] Surdeanu M, Harabagiu S. Using the Semantic Web for Legal Knowledge Representation. Artificial Intelligence and Law, 2012, 20(3): 219-238.

[4] Kearns M, Roth A. The Ethical Algorithm: The Science of Socially Aware Algorithm Design. Oxford University Press, 2019.

[5] Katz D M, Bommarito M J, Blackman J. A General Approach for Predicting the Behavior of the Supreme Court of the United States. PLOS ONE, 2017, 12(4): e0174690.

[6] Susskind R. Tomorrow's Lawyers: An Introduction to Your Future. Oxford University Press, 2019.

[7] Binns R. Fairness in Machine Learning: Lessons from Political Philosophy. Proceedings of the 2018 Conference on Fairness, Accountability, and Transparency, 2018: 149-158.

[8] Raji I D, Buolamwini J. Actionable Auditing: Investigating the Impact of Publicly Naming Biased Performance Results of Commercial AI Products. Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 2019: 1-15.

[9] Chen J, Zhang L. Legal Text Classification Based on Deep Learning." Journal of Intelligent Systems, 2020, 29(1): 1-12.

[10] Lupu Y, Dagan I. A Survey of Text Mining in Legal Applications." Artificial Intelligence Review, 2019, 52(1): 1-24.

[11] Barlow J P, Brown C. Legal Knowledge Representation and Reasoning: A Survey. AI & Law, 2020, 28(2): 1-25.

[12] Chawla N V, Davis D. Bringing Big Data to Personalized Healthcare: A Patient-Centric Approach." Journal of Healthcare Informatics Research, 2013, 1(1): 1-26.

[13] Harlow C. The Role of AI in Legal Practice: Opportunities and Challenges. Harvard Law Review, 2022, 135(2): 1-45.

[14] Dastin J. Amazon Scraps Secret AI Recruiting Tool That Showed Bias Against Women. Reuters, 2018.

[15] Almeida G F, Nunes J L, Engelmann N, et al. Exploring the psychology of LLMs’ moral and legal reasoning. Artificial Intelligence, 2024, 333: 104145.

[16] Wang X, Zhang X, Hoo V, et al. LegalReasoner: A Multi-Stage Framework for Legal Judgment Prediction via Large Language Models and Knowledge Integration. IEEE Access, 2024.

[17] Casey B I, Niblett A. The Future of the Law: The Impact of Artificial Intelligence on Legal Practice." Stanford Law Review, 2017, 70(3): 1-24.

[18] Homoki P, Z?di Z. Large language models and their possible uses in law. Hungarian Journal of Legal Studies, 2024.

[19] Chlapanis O S, Androutsopoulos I, Galanis D. Archimedes-AUEB at SemEval-2024 Task 5: LLM explains Civil Procedure. 2024. arXiv preprint arXiv:2405.08502.

[20] Binns R. Fairness in Machine Learning: Lessons from Political Philosophy. Proceedings of the 2018 Conference on Fairness. Accountability, and Transparency, 2018, 149-158.

[21] Reiter J, Lentz B. Legal Decision Support Systems: A Review. Artificial Intelligence and Law, 2020, 28(2): 1-25.

[22] Tzeng J, Chen C. Legal Document Summarization: A Survey. ACM Computing Surveys, 2021, 54(6): 1-35.

[23] Surdeanu M, Harabagiu S. Using the Semantic Web for Legal Knowledge Representation." Artificial Intelligence and Law, 2012, 20(3): 219-238.

[24] D'Amour A, Kearns M. Fairness Through Awareness: A New Approach to Fairness in Machine Learning. Proceedings of the 37th International Conference on Machine Learning, 2020: 119-128.