Arijit Khan

Large Language Models for Blockchain Security and Analytics: A Survey

Large Language Models (LLMs) are transforming blockchain security and analytics, yet a systematic evaluation of their capabilities remains limited. This survey provides a comprehensive, AI‑centric assessment of LLM‑based methods across over 70 recent studies spanning 11 application domains, such as security auditing, t...

LLM-powered clustering for entity resolution

LLM-CER: An Interactive System for In-Context Clustering-Based Entity Resolution with Large Language Models

LLM-CER (LLM-powered Clustering-based ER), an interactive, end-to-end system that instructs LLMs to perform in-context clustering of records to reduce the number of costly LLM interactions while preserving high matching quality is introduced.

Inductive Correlation Clustering with Graph Neural Networks

This work uses Graph Neural Networks (GNNs) to solve Inductive Correlation Clustering, a novel generalization of the CC problem designed to handle unseen graph instances, and indicates that the method serves as an efficient pooling layer, enhancing the ability of GNNs to capture hierarchical structural information in n...