GaLM 2026: The 2nd International Workshop on Graph-Augmented LLMs (GaLM): Bridging Language and Structured Knowledge @ CIKM 2026

About the Workshop

Welcome to the 2nd Graph-Augmented LLMs (GaLM): Bridging Language and Structured Knowledge Workshop, taking place on November 8, 2026 at CIKM! This event brings together advanced graph machine learning, LLMs research and practical industrial applications. The first GaLM workshop was introduced at IEEE ICDM @ 2025.

The GaLM workshop explores the synergistic convergence of LLMs and graph-based methodologies and its applications with its transformative potential. This integration facilitates advancements in areas such as enhanced reasoning, improved contextual understanding, and robust generalization. We aim to foster discussions on leveraging Graph Neural Networks (GNNs) and graph representation learning to augment LLMs, as well as investigating the application of federated learning and unlearning techniques to address privacy and ethical concerns in this rapidly evolving field.

The workshop aims to foster a more accessible and collaborative research environment within this emerging field by democratizing access to graph-based methodologies within the broader NLP and LLM community and enhancing its awareness and adoption. This workshop aims to foster discussions on how graph structures can empower LLMs to achieve improved reasoning, knowledge integration, and data privacy in diverse applications, including but not limited to biomedical, environmental and social-economic systems with highly structured knowledge.

            Important Dates
            
                        Submission Deadline (Extended) 
                        August 31, 2026
                    
                        Acceptance Notification
                        September 23, 2026
                    
                        Workshop Date
                        November 8, 2026

Call for Papers

The aim of this workshop is to foster discussion around the emerging role of LLMs utilising graph data and computing techniques to enhance LLM capabilities and conversely, vice versa. We will invite original and unpublished research contributions to GaLM in relevant subjects, including, but not limited to:

Data cleaning, integration, and augmentation with graph-based LLMs
Graph-enhanced LLM architectures
LLMs for graph understanding and generation
LLM-driven graph processing
Graph representation learning and unlearning
Multimodal graph-LLM integration
Explainability, provenance, security, privacy, benchmarking for graph-based LLMs
Real-world applications of graph-enhanced LLMs in domains such as healthcare, finance, and social media.

Submission Requirements

Content: Authors are invited to submit full-length research papers, including those that have already been published elsewhere. Submissions should be relevant to the workshop theme and meet the standards of top-tier international research conferences.
Format: Manuscripts must be submitted in PDF format. Papers should follow the official ACM sigconf two-column template:
- Full papers: maximum 8 pages, plus unlimited pages for references, appendix and GenAI usage disclosure, presenting mature research results.
- Short papers: maximum 4 pages, plus unlimited pages for references, appendix and GenAI usage disclosure, presenting ongoing work, demos, position, or opinion papers.
Submitted papers will undergo single-blind review.
AI Tool Usage: LLM-generated text is prohibited unless part of the experimental analysis. AI tools may only be used for light editing (e.g., grammar checks).
We plan to publish accepted papers in CEUR Workshop Proceedings, subject to receiving a sufficient number of submissions.

Submission Link: https://openreview.net/group?id=ACM.org/CIKM/2026/Workshop/GaLM

Accepted Papers

Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism

Thushalika Kumar, Sukumar Kishanthan, Asela Hevapathige
Stratify Before Comparison: Encoding Diversity Beats Sampling Diversity as a Reliability Signal for the Weaker of Two LLM Graph Reasoners

Bharath Sreekumar Menon
Embedding-Based Multi-View Representation Learning and Seed-Driven Retrieval for Open-Ended Multi-Task Ranking

Aryaveer Singh, Jay Katukuri, Patrick Jeeva A, Saruchi, Smruthi Mukund, Ranchal Prakash
QFuse: Preserving Precise Queryability in Knowledge Graphs over Structured and Unstructured Data

Youngjune Kang, Jaehyung Yoon, Chae Eun Youn, Kyungeun Kim, Youngjae Kim
Cold-Start Link Prediction Needs a Ranking Readout

Yunha Kim, Young-Hak Kim, Tae Joon Jun
On the LLM Verification for Argument Graph Generation

Jakub Bąba, Jaroslaw A. Chudziak
FedMamba-V2X: A Federated Mamba-LLM Ensemble for Vehicular Intrusion Detection

ABHINAV DOGRA, AWANEESH KUMAR YADAV, Pradumn Kumar Pandey, An Braeken