Update session details for Sessions 2 and 1, correcting titles and descriptions for consistency

Author: soheilabadifard

2025/session-2.md

@@ -9,18 +9,14 @@ sidebartitle: Dec 08 - Session 2 - Next-Generation Semantic Systems: Knowledge G
 published: true
 ---
 
-Details about Session 3, 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.
+Details about Session 2, chaired by Hande McGinty and Kathleen Jagodnik:
 
 **Presentation Title:** LLM-Driven Knowledge Graphs: From Unstructured Text to Structured Insight
+**Presenter:** Dr. Alon Bartal
 
-Large Language Models (LLMs) have transformed how we interact with unstructured text, yet modern AI systems continue to struggle with the structured, interconnected data that underpins real-world decision-making. This talk introduces a hybrid paradigm that bridges this gap by integrating LLMs with Knowledge Graphs (KGs) and Graph Neural Networks (GNNs) to create transparent, domain-grounded, and actionable AI systems. After outlining the limitations of relying solely on unstructured data or structured data pipelines, I demonstrate how LLMs can be used to extract entities and relations from scientific literature, social media, and semi-structured biomedical resources, converting them into the semantic triples that populate large heterogeneous KGs. These enriched graphs serve as the foundation for powerful graph-based learning and prediction. Through three case studies: (1) cancer risk prediction integrating genomic, socioeconomic, and environmental features; (2) early detection of unreported side effects of GLP-1 receptor agonist drugs using biomedical knowledge and social media signals; and (3) classification of drug mechanisms (etiological vs. palliative) via heterogeneous KGs combined with GNNs, the talk illustrates how hybrid LLM-KG architectures outperform conventional approaches and enable new types of reasoning. Together, these results highlight a path toward scalable, explainable, continuously updated AI systems capable of capturing both the richness of unstructured text and the precision of structured knowledge, with implications for advancing healthcare, pharmaceuticals, risk modeling, and scientific discovery.
 
-**Presenter:** Dr. Alon Bartal
+**Abstract:**
+Large Language Models (LLMs) have transformed how we interact with unstructured text, yet modern AI systems continue to struggle with the structured, interconnected data that underpins real-world decision-making. This talk introduces a hybrid paradigm that bridges this gap by integrating LLMs with Knowledge Graphs (KGs) and Graph Neural Networks (GNNs) to create transparent, domain-grounded, and actionable AI systems. After outlining the limitations of relying solely on unstructured data or structured data pipelines, I demonstrate how LLMs can be used to extract entities and relations from scientific literature, social media, and semi-structured biomedical resources, converting them into the semantic triples that populate large heterogeneous KGs. These enriched graphs serve as the foundation for powerful graph-based learning and prediction. Through three case studies: (1) cancer risk prediction integrating genomic, socioeconomic, and environmental features; (2) early detection of unreported side effects of GLP-1 receptor agonist drugs using biomedical knowledge and social media signals; and (3) classification of drug mechanisms (etiological vs. palliative) via heterogeneous KGs combined with GNNs, the talk illustrates how hybrid LLM-KG architectures outperform conventional approaches and enable new types of reasoning. Together, these results highlight a path toward scalable, explainable, continuously updated AI systems capable of capturing both the richness of unstructured text and the precision of structured knowledge, with implications for advancing healthcare, pharmaceuticals, risk modeling, and scientific discovery.
 
-Alon Bartal, Ph.D. is an Assistant Professor (with tenure) and Director of the Information Systems Program at Bar-Ilan University’s Graduate School of Business Administration. His research combines AI-based analytical models, complex network analysis, and semantic technologies, integrating Knowledge Graphs, Large Language Models, and graph mining, to advance computational health, biomedical informatics, and social network analytics. He has developed AI-driven methods for detecting childbirth-related PTSD from clinical narratives, modeled drug and gene mechanisms for precision medicine, and studied bias in clinical documentation. His work in the mental health domain has been recognized repeatedly, including being highlighted by the U.S. National Institutes of Health (NIH) on its official Science Update news page in both 2023 and 2024. Dr. Bartal’s research has earned multiple distinctions, including the Best Theoretical Paper Award at the HICSS 53rd Conference, and it has been published in leading venues including the IEEE Journal of Biomedical and Health Informatics, IEEE Transactions on Knowledge and Data Engineering, and Bioinformatics.
+**Biography Dr. Alon Bartal:**
+Alon Bartal, Ph.D. is an Assistant Professor (with tenure) and Director of the Information Systems Program at Bar-Ilan University’s Graduate School of Business Administration. His research combines AI-based analytical models, complex network analysis, and semantic technologies, integrating Knowledge Graphs, Large Language Models, and graph mining, to advance computational health, biomedical informatics, and social network analytics. He has developed AI-driven methods for detecting childbirth-related PTSD from clinical narratives, modeled drug and gene mechanisms for precision medicine, and studied bias in clinical documentation. His work in the mental health domain has been recognized repeatedly, including being highlighted by the U.S. National Institutes of Health (NIH) on its official Science Update news page in both 2023 and 2024. Dr. Bartal’s research has earned multiple distinctions, including the Best Theoretical Paper Award at the HICSS 53rd Conference, and it has been published in leading venues including the IEEE Journal of Biomedical and Health Informatics, IEEE Transactions on Knowledge and Data Engineering, and Bioinformatics.

2025/session-6.md

@@ -1,16 +1,16 @@
 ---
 layout: page
-title: Dec 08 - Session 3 - Bridging Memory and Machine: Semantic Technologies for Historical Research in the Age of AI
+title: Dec 08 - Session 1 - Bridging Memory and Machine: Semantic Technologies for Historical Research in the Age of AI
 author: Antrea Christou
 permalink: /2025/session-6
 mainnav: false
 sidenav: false
-sidebartitle: Dec 08 - Session 3 - Bridging Memory and Machine: Semantic Technologies for Historical Research in the Age of AI
+sidebartitle: Dec 08 - Session 1 - Bridging Memory and Machine: Semantic Technologies for Historical Research in the Age of AI
 published: true
 ---
 
 
-Details about Dec 8 Session 2, chaired by Dean Rehberger and Walter Hawthorne:
+Details about Dec 8 Session 1, chaired by Dean Rehberger and Walter Hawthorne:
 
 The discipline of history stands at a peculiar crossroads. Large language models now generate plausible-sounding narratives about the past with alarming fluency. Yet, they do so without genuine comprehension of causation, context, or the intricate web of evidence that undergirds historical interpretation.  Meanwhile, historians possess centuries of methodological rigor for evaluating sources, tracing provenance, and constructing arguments from fragmentary evidence—precisely the kind of structured reasoning that semantic technologies were designed to formalize and make explicit.