GRIT @ SIGIR-AP 2026

Generative Information Retrieval in the Wild: Foundations and Real-World Readiness

GRIT (Generative Information Retrieval in the Wild) is a workshop at SIGIR-AP 2026 focused on the real-world readiness of generative information retrieval (GenIR). Generative information retrieval reformulates retrieval as sequence generation, directly generating identifiers of relevant targets. Beyond document retrieval, this paradigm has expanded to generative recommendation, multimodal and cross-modal retrieval, code retrieval, and entity retrieval.

GRIT focuses on GenIR beyond benchmark accuracy, bringing together research on foundations and probing, reliability and robustness, continual adaptation, scalability and efficiency, evaluation beyond relevance, and deployment experience. The workshop focuses on systems where generation is the retrieval mechanism itself, including document and passage retrieval, generative recommendation, multimodal and cross-modal retrieval, entity retrieval, product search, and code retrieval. Systems that use generative models only as auxiliary components, such as query expansion, summarization, answer generation, or standard RAG pipelines, are outside the core scope unless retrieval itself is performed through generation.

More information is available on the workshop website.

Submission Guidelines

GRIT solicits short papers of up to 4 pages, including references, in the ACM two-column format. Submissions should be double-anonymous: author names, affiliations, and other identifying information should be removed from the manuscript. We welcome academic and industrial submissions, including case studies, experience reports, position and vision papers, open problems, preliminary ideas, research findings, system analyses, benchmarks, and negative results related to the real-world readiness of retrieval-by-generation systems. Authors may use the ACM proceedings template or the Overleaf template. Please also follow the official SIGIR-AP 2026 paper submission instructions.

List of Topics

Topics of interest include, but are not limited to:

• Foundations and Probing: Understanding, interpreting, and diagnosing retrieval-by-generation systems; representation of target collections; and relationships between generation likelihood, relevance, preference, and utility.
• Reliability and Robustness: Reliable generation under noisy, ambiguous, adversarial, and out-of-distribution inputs; invalid, duplicated, hallucinated, or poorly calibrated generations.
• Resilience and Continual Adaptation: Dynamic collections, insertions, deletions, updates, cold-start targets, temporal shifts, continual learning, and machine unlearning.
• Scalability and Efficiency: Training, indexing, updating, serving, latency, memory, throughput, and energy efficiency at realistic scales.
• Evaluation Beyond Relevance: Updateability, coverage, diversity, novelty, long-tail accessibility, fairness, privacy, robustness, and user- or session-level utility.
• Deployment and Industrial Experience: Real-world deployments, system analyses, monitoring practices, hybrid architectures, success stories, failure cases, and negative results involving retrieval-by-generation systems.

Review Process

Each submission will receive at least two reviews. Decisions will consider relevance, clarity, technical soundness where applicable, discussion potential, and balance across workshop topics. Standard conflict-of-interest procedures will be followed. Accepted papers will be presented as lightning talks, posters, demonstrations, or breakout discussion inputs.

Important Dates

All deadlines are 11:59 PM AoE (Anywhere on Earth) unless noted otherwise.

• Paper submission deadline: September 25, 2026
• Notification of acceptance: October 15, 2026

Organizing Committee

• Yubao Tang, University of Amsterdam
• Xinyu Lin, National University of Singapore
• Bhuvesh Kumar, Snap Inc.
• Maarten de Rijke, University of Amsterdam

Contact

All questions about submissions should be emailed to grit-sigir-ap2026@googlegroups.com.