U.S. Semantic Technologies Symposium Series
Dec 08 - Session 2 (Hande)
Details about Session 2, chaired by Hande McGinty and Kathleen Jagodnik:
Knowledge Graphs (KGs) and Large Language Models (LLMs) are reshaping semantic technologies from complementary directions. KGs provide structured, explicit, and explainable representations of knowledge, while LLMs excel at capturing linguistic patterns and enabling natural, generative interaction. This symposium will examine each approach individually as well as hybrid systems that integrate them. Topics include KG construction; ontology alignment; semantic reasoning; LLM-based information extraction, evaluation and benchmarking; and trustworthy deployment. We will also highlight emerging strategies for bridging the two paradigms, such as retrieval-augmented generation (RAG), ontology-guided prompting, and KG-based semantic validation of model outputs.
This session will include two Keynote Presentations, Lightning Talks presenting overviews of the projects included in the subsequent Poster Session, a Breakout Session to develop a Perspective/Review article proposing future directions for the integration of KGs and LLMs to advance semantic technologies, and a Plenary Discussion to integrate the day’s activities and discuss a path forward.
By bringing together researchers and practitioners from academia, industry, and government, this session aims to spark dialogue across traditionally distinct communities. Participants will explore applications, design patterns, and ethical challenges, while charting a path toward sustainable, transparent, and knowledge-aware AI systems.