Call for Papers
Submit on EasyChairImportant Dates
-
Submissions OpenJuly 15, 2026
-
Submission DeadlineAugust 24, 2026 AoEUpcoming
-
Accept/Reject NotificationSeptember 23, 2026Upcoming
-
WorkshopNovember 8, 2026Upcoming
We invite researchers to submit their latest work to the KEIR @ CIKM 2026 workshop on various aspects of knowledge-enhanced information retrieval, including models, techniques, data collection, and evaluation methodologies. We welcome both short and long papers reporting original or work-in-progress research, as well as position, applied, and resource papers and demos.
We broadly define external knowledge as any resource beyond a model's parametric memory—unstructured or structured, gold or synthetic, and increasingly multimodal—including text corpora, tabular data, semi-structured user preferences, knowledge graphs, and databases. We particularly encourage contributions targeting knowledge-intensive, domain-sensitive fields such as science, medicine, law, and finance, where factuality, trust, and discovery are paramount.
Relevant Topics Include, but are not limited to:
- Knowledge-enhanced information retrieval and recommendation models, both representational and generative (e.g., generating document identifiers grounded in domain knowledge)
- Knowledge-enhanced language models for retrieval
- Knowledge-enhanced retrieval-augmented generation models
- Knowledge-enhanced approaches for data augmentation and query processing, including query parsing, expansion, relevance feedback, and reformulation
- Knowledge-enhanced agentic IR: LLM agents that plan, reason, and decide when, what, and how to retrieve, navigate structured knowledge, and curate and link knowledge
- Self-evolving, dynamic-knowledge, and automated discovery frameworks driving new paradigms for AI4Science
- Multimodal knowledge sources and modality-specific IR techniques (e.g., visual patches from PDF pages, subgraph retrieval from knowledge graphs)
- Test-time training and adaptation of retrievers and language models to incorporate new knowledge
- Efficiency at both training and inference time (e.g., knowledge distillation, adapters, and latency reduction)
- Applications of knowledge-enhanced retrieval, such as dialogue systems, question answering, and summarization in domain-specific settings
- Evaluation methodologies for knowledge-enhanced IR, including uncertainty quantification, interpretability, attribution, and analysis of bias and fairness