1st CfP - SynIRgy 2026: Synthetic Data and Simulation Synergy for Information Retrieval

Co-located with ECIR 2026: The 48th European Conference on Information Retrieval 

April 2, 2026. Delft, The Netherlands.

This workshop aims to explore the increasing role of simulation and synthetic data in information retrieval (IR). While traditional IR research has long relied on static benchmark datasets such as TREC collections, as well as fixed recommendation datasets like MovieLens and the Netflix Prize, these datasets only partially capture the complexity of real-world environments. In practice, information access systems, including search and recommendation, are highly dynamic and interactive. Static evaluation methods fail to capture user adaptation, long-term effects, and challenges such as filter bubbles, fairness, and causal reasoning. The workshop aims to bridge this gap by bringing together researchers and practitioners to discuss best practices, emerging methodologies, and open challenges in simulation-based IR research.

Submission Instructions

Submission Guideline

Authors should consult Springer's authors' guidelines and use their proceedings templates, either for LaTeX or for Word (to be found at https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines), for the preparation of their papers. Springer encourages authors to include their ORCIDs in their papers (https://www.springer.com/gp/authors-editors/orcid). 

All submissions must be written in English. All papers should be submitted electronically through the EasyChair submission system. The EasyChair URL for submissions is as follows: https://easychair.org/cfp/SynIRgy2026.

Authors have to first submit the abstract of their paper by January 15, 2026, 11:59pm (AoE). The title and abstract have to be representative of the paper content, as they will be used during the bidding process by reviewers. The paper submission deadline is on January 19, 2026, 11:59pm (AoE).

In addition, the corresponding author of each accepted paper, acting on behalf of all of the authors of that paper, must complete and sign a Consent-to-Publish form. The corresponding author signing the copyright form should match the corresponding author marked on the paper. Once the paper has been submitted, changes relating to its authorship cannot be made.

Accepted papers will be published in the workshop proceedings in the Springer Lecture Notes in Computer Science series. The proceedings will be distributed to all delegates at the conference. Accepted papers will have to be presented at the conference by one of the authors in person, and at least one author for each accepted contribution will be required to register and attend.

Submission Types

All papers must be original and not simultaneously submitted to another journal or conference. The following paper categories are welcome:

• Full research papers (12 pages)

• Short papers and work-in-progress (4--6 pages)

• Demo papers (5 pages)

• Negative results papers (6--8 pages)

• Position papers (4--6 pages), which may take one of three forms:

  • Opinion papers: Present well-argued perspectives on topics relevant to the workshop.

  • Research methodology papers: Outline methodological approaches, identify key challenges, propose potential solutions, and highlight open questions. 

  • Short survey papers: Provide an overview of a specific topic under the themes, highlighting critical challenges and future directions.

While full experiments are not required for position papers, authors are encouraged to include preliminary results, illustrative examples, or real-world use cases where applicable.

Important Dates

• Abstract submission: January 15, 2026
• Paper submission: January 19, 2026
• Decision notification: February 13, 2026
• Camera ready: February 23, 2026
• Workshop day: April 2, 2026

List of Topics

The topics of interest include, but are not limited to:

• User behavior & interaction
  • How can we model realistic user interactions in simulated IR, including using LLMs to generate behavior that mimics real-world users?
  • How do synthetic user profiles compare to real-world data, and how can their effectiveness be validated?
• Synthetic data generation
  • What metrics can assess similarity between real and synthetic data?
  • How can we generate synthetic datasets that preserve utility while ensuring privacy?
  • How do we measure the similarity between real and synthetic data, and what trade-offs exist between privacy preservation and retrieval model accuracy?
  • How can LLMs be fine-tuned to create high-quality datasets, and how can these be validated for real-world applicability?
  • Which aspects of real-world performance in information access (e.g., search and recommendation) can be evaluated with synthetic data, and how can we ensure that synthetic data faithfully reflects user behavior and system dynamics?
• Algorithm development & evaluation
  • What conditions must a simulation environment meet to support algorithm development?
  • What role can simulation play in advancing reinforcement learning for interactive information access systems?
  • In which scenario/use case is synthetic data valid for evaluation and algorithm development?
  • How can RAG pipelines be simulated and evaluated, and what benchmarks are needed to assess their performance?
• Bias and Ethics
  • How can synthetic data mitigate bias in information retrieval systems, and what trade-offs arise when balancing fairness, utility, and privacy?
  • What ethical concerns emerge when using LLMs to generate synthetic data for IR, e.g., regarding transparency, accountability, and potential misuse? 
  • How can user personas created for simulations ensure diversity and inclusivity?
  • What methods can help prevent the reinforcement of existing biases?
• Reproducibility & infrastructure
  • How do we define reproducibility in synthetic data and simulations, and what standardization efforts are needed for better comparability?
  • How can we apply FAIR (Findable, Accessible, Interoperable, Reusable) principles for transparent and repeatable experiments, and can LLMs assist in automating reproducibility evaluations?
  • What role do open-source tools and cloud computing play in facilitating scalable simulation environments?

Organizing committee

• Manel Slokom
• Alejandro Bellogin
• Andrea Barraza-Urbina
• Mayank Singh

Publication

SynIRgy2026 proceedings will be published in LNCS by Springer.

Venue

The conference will be co-located with ECIR 2026: The 48th European Conference on Information Retrieval, taking place in Delft, The Netherlands.

Contact

All questions about submissions should be emailed to synirgy@outlook.com .