Research & Publications

Exploring the intersection of artificial intelligence and legal technology through rigorous research and practical applications.

Research Areas

My research focuses on the practical application of AI in legal systems

⚖️

AI in Law

Exploring applications of Artificial Intelligence and Machine Learning in legal documents, legal research, policy analysis, and related tasks.

Chained AI Agents

Designing autonomous chains of specialized large models to perform complex tasks, such as mult-step literature reviews and knowledge synthesis.

🟣

Deterministic, Low-Complexity Clustering Methods

Developing O(n) methods to match or outperform k-Means++, reducing randomness and improving convergence in large datasets.

🚀

Cloud-native and Containerized Computing

Designing lightweight primitives and orchestration mechanisms to efficiently manage resources in clouds and clusters.

Publications

Research papers and ongoing work in AI and legal technology

Accepted
2025

Feasibility of Artificial Intelligence Driven Analysis in the Context of Nepalese Legal System

ICAIL 2025
Abhiyan Dhakal, Sugat Sujakhu, Pranish Kafle, Kausik Paudel, Prakash Poudyal

AI-driven legal analysis for Nepal uses ML and RAG to streamline judicial processes and boost accessibility with precise document retrieval.

Abstract

We proposed an innovative solution through an Artificial Intelligence driven legal analysis customized to the utility of the Nepalese legal context. Using advanced machine learning (ML) models and Retrieval-Augmented Generation (RAG) techniques, the research provides legal insights, streamlines judicial processes, and enhances accessibility to legal information. The legal documents were processed to convert into JSON format, and then to convert into vector data. GPT-4o was used for query expansion and response generation, whereas text embeddings were generated through text-embedding-ada-002. Key features include efficient document retrieval and query expansion for enhanced search precision. The model performs well across different query types, achieving an 𝐹1 score of 0.797 for rule-recall, 0.857 for rhetorical understanding, and 0.875 for interpretation-based queries. This work marks a significant step towards integrating AI into the legal domain of Nepal.

Interested in Collaboration?

I'm always open to collaborating on research projects, particularly in AI, legal technology, and interdisciplinary studies.

Discuss Research