LLMs and Graphs Synergy

In this episode, Garima Agrawal, a senior researcher and AI consultant, brings her years of experience in data science and artificial intelligence. Listeners will learn about the evolving role of knowledge graphs in augmenting large language models (LLMs) for domain-specific tasks and how these tools can mitigate issues like hallucination in AI systems.

Key insights include how LLMs can leverage knowledge graphs to improve accuracy by integrating domain expertise, reducing hallucinations, and enabling better reasoning.

Real-life applications discussed range from enhancing customer support systems with efficient FAQ retrieval to creating smarter AI-driven decision-making pipelines.

Garima’s work highlights how blending static knowledge representation with dynamic AI models can lead to cost-effective, scalable, and human-centered AI solutions.

Guest

Garima Agrawal: Garima Agrawal is the founder of HumaConn LLC, a consulting firm dedicated to empowering businesses and investors with tailored AI solutions. HumaConn specializes in designing strategies for AI integration to enhance efficiency, streamline processes, and identify high-potential AI startups, bridging innovation with real-world applications. She is also a Senior Researcher and AI Consultant at Minerva CQ, based in California, USA. Garima recently completed her Ph.D. in Artificial Intelligence from Arizona State University (ASU), where her research focused on developing knowledge-aware AI for domain-specific question-answering systems. She specializes in constructing knowledge graphs from unstructured data to support emerging domains. Her broader research interests include domain knowledge representation, generative AI, conversational AI, reducing hallucinations, LLM cost optimization, improving RAG pipeline, knowledge graphs, adversarial learning, and applying machine learning to cybersecurity. With over 12 years of industry experience as a software engineer, data scientist, and engineering manager, Garima blends practical expertise with academic rigor, delivering innovative solutions that drive meaningful impact.