HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Mon, 04 Aug 2025 12:23:39 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"6890a64b-18fa" expires: Tue, 30 Dec 2025 10:15:12 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 95BB:36A0B4:9EEFEA:B27B63:6953A3D8 accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 10:05:12 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210020-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767089113.761398,VS0,VE218 vary: Accept-Encoding x-fastly-request-id: 7e3cb8fb794a3175a2f54406ea24100cbcc9b5b3 content-length: 2225

Overview

Schedule

Speakers

Committee

Call For Papers

We invite researchers working on structured data retrieval and reasoning with Large Language Models (LLMs) to submit their latest original research work to the KDD 2025 workshop on Structured Knowledge for Large Language Models

• Submission link: Open Review
• Submission deadline: May 26th, 2025 (11:59 pm AoE)  —  May 30th, 2025 (11:59 pm AoE)
• Acceptance notification: July 4th, 2025 (anytime before 11:59 pm AoE)
• Workshop time: August 4th, 1pm to 5pm, 2025

For any questions, please reach out to us at sknowllm-organizers@googlegroups.com.

Scope and Topics

We invite submissions related to the theme of structured knowledge for large language models. Key topics include, but are not limited to:

• Retrieved-augmented generation (RAG) and in-context learning and (ICL) with structured data (e.g., tables, graphs, images, and time series)
• LLM pre-training and fine-tuning techniques across heterogeneous structured knowledge sources
• Structure/knowledge-enhanced post-training for LLM alignment
• Constructing Structured Knowledge Bases with LLMs
• Natural language and symbolic reasoning with structured knowledge
• Trustworthiness of structure/knowledge-enhanced LLMs
• Benchmarks and datasets combining proprietary structured and unstructured data sources
• LLM-based agents interacting with structured enterprise data
• Domain-specific applications (e.g., e-commerce, science, finance, and industry) of structured knowledge in LLMs
• LLMs for reasoning, and generation tasks for structured data

Submission Instructions

• Papers should be between 4 to 8 pages excluding references and appendices.
• Submissions should be made on Open Review in a single .pdf file using the official KDD 2025 submission template available at Overleaf.
• The review process is double-blind, so please ensure that your submission is properly anonymized.
• Please note that there is no rebuttal phase and the final decisions will be made based solely on the submission and the reviews.
• Rejected and withdrawn submissions will not be made public.
• Parallel submission of papers under review at KDD 2025 is allowed. If a paper is currently under review at another venue, it can still be submitted to this workshop.
• If a paper has previously appeared in a journal, workshop, or conference, it should be reasonably extended in order to be accepted at this workshop.

All accepted submissions will be accompanied by a poster presentation. A number of selected submissions will be invited for oral presentations.

Organizers