LLMs and Graphs Synergy

Powerful models become much more interesting when we look at what is happening underneath. 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.

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.