Special Track on Knowledge Graphs and RAG on the Web (WeKGR 2026)
Large Language Models (LLMs) have transformed web-based information systems, yet they suffer from critical limitations, most notably hallucination, where models generate fluent but factually incorrect content, as well as outdated parametric knowledge, lack of traceability, and poor structured reasoning. These issues pose serious risks for knowledge-intensive web applications. Graph-based approaches offer principled solutions: knowledge graphs provide verifiable, structured representations of world knowledge; Graph Neural Networks (GNNs) enable relational reasoning over connected data; and Graph Retrieval-Augmented Generation (GraphRAG) grounds LLM outputs in structured evidence, directly mitigating hallucination and improving factual consistency. Explainability methods further ensure that graph-based predictions are interpretable and auditable. Despite their complementary nature, these research threads remain largely addressed in isolation.
WeKGR 2026 bridges this gap by providing a dedicated forum at WISE 2026 to advance graph-based approaches for building trustworthy, grounded, and explainable web information systems.
- Temporal, dynamic, and evolving knowledge graphs for the Web
- Multi-relational graph representation learning for the Web
- Cross-lingual and multilingual knowledge graphs for Web information systems
- Scalable GNN training and inference for large web graphs
- Post-hoc explanation methods for GNNs based Web systems
- Fairness, bias detection, and debiasing in Web graph AI
- Causal reasoning over graph-structured web data
- GraphRAG architectures and pipelines for the Web
- Factual consistency verification using Web knowledge graphs
- Agentic LLM systems and graph-structured Web knowledge
- Graph-based question answering and Web information retrieval
- Privacy, security, and ethical considerations in graph-LLM systems
- Graph-powered recommendation, search, and personalisation on the Web
All submissions for this special track must be written in English and conform to the Springer LNCS proceedings format with the following page limits: 15 pages for papers including references. Submitted papers will undergo a “double-blind” review process, coordinated by the Program Committee. To ensure anonymity of authorship, authors must ensure that authors’ names, affiliations, funding, and any other identifying information of authorship do not appear on the title page or elsewhere in the paper. Authors must provide the complete and final list of authors at the submission stage. No addition, removal, or change in the order of authors is allowed after submission.
Please use one of the following templates for the LNCS (Lecture Notes in Computer Science) format: https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines
All paper submissions for this special track will be via Microsoft CMT (under “Special track on Knowledge Graphs and RAG on the Web”).
The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.
| Paper Submission | June 17, 2026 |
| Acceptance Notification | July 20, 2026 |
| Camera Ready | August 25, 2026 |
*All deadlines are 23:59 Anywhere on Earth time.
- Wissem Inoubli (CRIL, Univ. Artois) <[email protected]>
- Salma Sassi ( ECE Engineering School ) <[email protected]>
- Haithem Mezni (Jendouba University) <[email protected]>
- Sabeur Aridhi (inria – CNRS, University of Lorraine) <[email protected]>
- Hassan Soubra (ECE Engineering School) <[email protected]>
Wissem Inoubli (CRIL, Univ. Artois) <[email protected]>
