IDEAS 2026
30th International Database Engineered Applications Symposium
Concordia University
May 20 - 22, 2026,
Montreal, Canada
The symposium provides an international forum for discussion of the problems of engineering data drivend systems involving not only database technology but the related areas of information retrieval, multimedia, human machine interface and communication. The goal of IDEAS is to foster closer interaction among the industrial, research and user communities and provides an excellent opportunity for them to meet, discuss ideas, examine the current ones and develop new solutions and research directions. Along with the technical sessions, the symposium also features prominent invited speakers.
IDEAS series of symposiums are scheduled annually and have been held since 1997 in North America, Europe and Asia. It has attracted participants from governmental and non-governmental agencies, industries, and academia to exchange ideas and share experiences.
Organized by
Concordia University, Montreal, Canada; with the cooperation of BytePress and ConfSys.
The conference proceedings will be published in the LNCS(Springer). series.
Invited Talk
Empowering Large Language Models with Knowledge Structuring and Reasoning
Abstract
Large language models (LLMs) have demonstrated significant potential in query answering, reasoning and decision support. Yet LLMs still suffer from hallucinations and lack fine-grained contextual domain-specific knowledge, limiting their power of in-depth reasoning/prediction in many scientific problem-solving applications. Traditional retrieval-augmented generation (RAG) methods attempt to address these limitations but frequently retrieve less relevant and unstructured information, undermining reasoning and prediction accuracy. We propose a retrieving-structuring-reasoning approach to mine structures from unstructured data, retrieving more relevant information upon a query, and construct task-specific graphs using the mined structures to facilitate structure-augmented LLM generation. We show such a retrieving and structuring-augmented generation will enhance the power of complex reasoning/prediction with LLMs. We will discuss some interesting research issues in this direction as well.
Short bio
Jiawei Han is Michael Aiken Chair Professor in the Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign. He received ACM SIGKDD Innovation Award (2004), IEEE Computer Society Technical Achievement Award (2005), IEEE Computer Society W. Wallace McDowell Award (2009), Japan's Funai Achievement Award (2018), and being elevated to Fellow of Royal Society of Canada (2022). He is Fellow of ACM and Fellow of IEEE and served as the Director of Information Network Academic Research Center (INARC) (2009-2016) supported by the Network Science-Collaborative Technology Alliance (NS-CTA) program of U.S. Army Research Lab and co-Director of KnowEnG, a Center of Excellence in Big Data Computing (2014-2019), funded by NIH Big Data to Knowledge (BD2K) Initiative. Currently, he is serving on the executive committees of two NSF funded research centers: MMLI (Molecular Maker Research Institute)—one of NSF funded national AI centers since 2020 and I-Guide—The National Science Foundation (NSF) Institute for Geospatial Understanding through an Integrative Discovery Environment (I-GUIDE) since 2021.
Paper due date: 22 March, 2026 Extended Deadline
Acceptance notification: 27 April 2026
Final Version upload to ConfSys etc.: 1 May, 2026
Please refer to the following guides - these would be useful: - https://confsys.encs.concordia.ca/public_files/guidelines.php - https://confsys.encs.concordia.ca/ConfSysAuthorFAQ.php
TOPICS
A list of non-exhaustive topics can be found at:
https://confsys.encs.concordia.ca/IDEAS-II/ideas26/ideas26_topics.php
- Co-ops & Sponsors
-
-
