Leveraging Knowledge Graphs and LLMs for Context-Aware Messaging
Rajeev Kumar, Harishankar Kumar, Kumari Shalini
TL;DR
The paper tackles the need for context-aware, personalized messaging in critical domains by proposing a Context-Aware Messaging System that fuses knowledge graphs, real-time event data, and fine-tuned large language models. The approach links entities in user messages to KG nodes, enriches them with current context, and generates tailored outputs via LLM prompts, with a feedback loop for continuous improvement. Key findings include domain-specific acceptance rates (healthcare ~42%, education ~53%, recruitment ~78%), demonstrating gains from real-time data integration and model fine-tuning. The work offers a scalable framework for audience-specific communication with potential for active learning, domain metrics, and broader applicability to healthcare, education, and recruitment.
Abstract
Personalized messaging plays an essential role in improving communication in areas such as healthcare, education, and professional engagement. This paper introduces a framework that uses the Knowledge Graph (KG) to dynamically rephrase written communications by integrating individual and context-specific data. The knowledge graph represents individuals, locations, and events as critical nodes, linking entities mentioned in messages to their corresponding graph nodes. The extraction of relevant information, such as preferences, professional roles, and cultural norms, is then combined with the original message and processed through a large language model (LLM) to generate personalized responses. The framework demonstrates notable message acceptance rates in various domains: 42% in healthcare, 53% in education, and 78% in professional recruitment. By integrating entity linking, event detection, and language modeling, this approach offers a structured and scalable solution for context-aware, audience-specific communication, facilitating advanced applications in diverse fields.