The annual SIGIR-AP (Asia/Pacific) conference is a new regional conference on Information Retrieval. The 3rd SIGIR-AP conference (SIGIR-AP 2025) will be a hybrid conference from December 7th to 10th, 2025, in Xi'an, China. The authors of accepted papers can present their work in person or remotely at the conference. The scope of SIGIR-AP is the same as that of SIGIR. We welcome high-quality papers with contributions related to information retrieval. There are two types of SIGIR-AP submissions: Regular submissions and SIGIR-Revise-and-Resubmit submissions.

Regular Submissions

Regular submissions are new, original contributions that have not been accepted elsewhere or simultaneously submitted to another journal or conference. We welcome the following types of submissions:

Original research papers that make new theoretical and / or empirical contributions to the field of IR that grow our scientific understanding of models, systems, metrics, and user interactions in IR to aid the development of more effective information access methods;

Resource papers that describe new resources available to the community, including test collections, software tools, and services for information retrieval and access tasks;

Reproducibility papers that repeat, reproduce, generalize, and re-examine prior work, with the focus on generating new findings of established approaches akin to a test of time;

Industry papers that describe IR systems in practice, open problems and challenges in industry, and challenges and best practices for taking research to production;

Perspective papers that describe original ideas and research visions for new or open problems in IR, or provide novel and critical perspectives on existing IR research.

We encourage authors to make as many of the resources associated with a paper publicly available.

SIGIR-Revise-and-Resubmit (SIGIR-RR) Submissions

SIGIR-RR submissions are for revised manuscripts of either full, short, resource, reproducibility, and perspective papers that were submitted to but not accepted by the SIGIR 2025 conference. Authors can use this option to address the issues raised in the SIGIR 2025 reviews and revise the paper accordingly. In addition to the revised paper, the authors must attach the following information to the submitted PDF file:

Explanation (1-3 pages with no style requirements): a text includes the SIGIR paper ID and responses to the SIGIR reviews, explaining how the issues raised by the SIGIR reviewers have been addressed in the revised paper.

SIGIR submission: the original anonymized submission file to SIGIR 2025.

Authors take note: It is up to the authors to decide if they want to resubmit their paper (that was previously submitted to SIGIR but not accepted) as a SIGIR-RR submission or as a regular submission. Both are allowed. We anticipate that papers going through the SIGIR-RR process will have a higher chance of being accepted if the issues in the SIGIR reviews are fixed compared to a resubmission via the regular submission process. This might, of course, vary on a case-by-case basis. We encourage authors to use their best judgment to decide which path may be more appropriate for their specific submission.
In cases of resource and reproducibility papers, please be aware that the review process for SIGIR 2025 was single-blind, while for SIGIR-AP 2025 it is double-blind. Please ensure that your SIGIR-RR submission is adequately anonymized (including both the manuscript and the responses to the SIGIR reviews).

Important Dates for Paper Submissions

Time zone: Anywhere On Earth (AOE)
Abstracts due: July 1st, 2025
Paper due: July 8th, 2025
Notification: September 12th, 2025
Camera-ready due: September 26th, 2025

Submission Guidelines

All submissions of papers must be original and have not been published or accepted elsewhere or simultaneously submitted to another journal or conference.

Submissions of regular and SIGIR-RR papers must be in English, in PDF format, in the current ACM two-column conference format. Suitable LaTeX, Word, and Overleaf templates are available from the ACM Website (use the "sigconf" proceedings template for LaTeX and the Interim Template for Word).

We adopt a double-anonymized, single-track reviewing procedure, which allows submissions of papers commensurate with their contribution sizes (i.e., we don't have two tracks for full and short papers, respectively).

Submissions of papers must be at least 2 pages and at most 9 pages (including figures, tables, proofs, appendixes, acknowledgments, and any content except references) in length, with unlimited pages for references. While we do not set separate submission tracks for full and short papers, the assessment of each submission will be based on whether the paper length is commensurate with its contribution. For example, a 2-page paper would be accepted if its scientific contribution is worth 2 pages. However, a 9-page paper would be considered weak if it only contains the substance of a 4-page paper.

Submissions must be anonymous and should be submitted electronically via EasyChair.

Submission Policies

Anonymity and Pre-Print/ArXiv Policy: The review process is double-anonymized. Authors must take all reasonable steps to preserve the anonymity of their submissions. The submissions must not include any author information. The citations and discussions of authors' prior work should be anonymized or written in the third person form. It is acceptable to explicitly refer to companies or organizations that provided datasets, hosted experiments, or deployed solutions if it does not necessarily imply the authors are affiliated with these mentioned organizations. The authors can submit to SIGIR-AP 2025 papers that have been posted to pre-print/archival platforms (e.g., arXiv) or will be posted in the future, after submission. In such cases, the authors should take reasonable actions to make the submission non-discoverable, e.g., by changing the title of the submission. SIGIR-AP follows the SIGIR 2025 Pre-Print/ArXiv Policy, and breaking anonymity or pre-print/ArXiv policy puts the submission at risk of being desk rejected. Anonymity of Resource Papers: We recognize that anonymization of online resources is not always possible, and therefore, we ask authors to take reasonable (not onerous) actions to make the online resources anonymous. Anonymization is not needed for existing resources that are already used by the community. Authors' names should always be removed from the paper.
Anonymity of Industry Papers: We recognize that full anonymization of industry papers is not always possible, especially if the paper is about systems / platforms / resources that make it easy to identify the institution. Therefore, we ask authors to take reasonable (not onerous) actions to make the papers anonymized. It is acceptable to explicitly refer to companies or organizations that provided datasets, hosted experiments, or deployed solutions. Authors' names should always be removed from the paper.
Desk Rejection Policy: Submissions that violate the anonymity policy and pre-print policy, do not adhere to formatting or length requirements, lack topical fit for SIGIR, or are determined to violate ACM’s policies on academic dishonesty, including plagiarism, author misrepresentation, falsification, etc., are subject to desk rejection by the chairs.
Authorship Policy: Authors should carefully read ACM's authorship policy before submitting a paper. To identify reviewers with conflicts of interest, the full author list must be specified at abstract submission time. Changes to the author list after the abstract submission are not allowed. At least one author of each accepted paper should register for the conference and present the work, either in person or remotely, at the conference.
ACM Publication Policy: By submitting your article to an ACM Publication, you are hereby acknowledging that you and your co-authors are subject to all ACM Publications Policies, including ACM's new Publications Policy on Research Involving Human Participants and Subjects. Alleged violations of this policy or any ACM Publications Policy will be investigated by ACM and may result in a full retraction of your paper, in addition to other potential penalties, as per ACM Publications Policy. Please ensure that you and your co-authors obtain an ORCID ID, so you can complete the publishing process for your accepted paper. ACM has been involved in ORCID from the start, and we have recently made a commitment to collect ORCID IDs from all of our published authors. We are committed to improving author discoverability, ensuring proper attribution, and contributing to ongoing community efforts around name normalization; your ORCID ID will help in these efforts.

TOPICS OF INTEREST

The topics of SIGIR-AP are the same as those of SIGIR. Relevant areas include but are not limited to:

Search and Ranking:

Research on core IR concepts, principles, and algorithms:

Queries and query analysis
Web search
Retrieval and ranking models
Theoretical models and foundations of information retrieval and access

System, Efficiency, Scalability, and Sustainability:

Research on system aspects related to the efficiency and scalability of IR systems:

Efficient and scalable crawling, indexing, ranking, and more
Energy efficiency and green computing for IR
Scalable and sustainable platform architecture, distributed search, metasearch, peer-to-peer search, search in the cloud, edge IR

Recommender Systems:

Research on recommender systems:

Filtering and recommendation
Cross-domain recommendation, socially- and context-aware recommender systems, multi-stakeholder recommendations
Interactive and conversational recommendation
Evaluation of recommender systems
Other theoretical models and foundations of recommender systems

Machine Learning and NLP for IR:

Research that bridges ML, NLP, and IR:

ML applied to IR
Generative IR, including large language models for IR
Retrieval enhanced machine learning (REML) and Retrieval augmented generation (RAG)
Question answering

Conversational IR:

Research on developing intelligent IR systems that support interactive conversations with users:

End-to-end conversational IR models and optimization
Modularized IR techniques (e.g., query understanding, user modeling, intent prediction, context and discourse management, reranking, and results presentation)
Session-based search or recommendation, user engagement
Conversational question answering
Intelligent personal assistants and agents

Humans and Interfaces:

Research on user-centric aspects of IR, including user interfaces, behavior modeling, privacy, and interactive systems, such as:

Mining user activity logs and modeling users
User simulation
Interactive search
Social search
Collaborative search
Information security
User studies
Other theoretical models and foundations of user-centric IR

Evaluation:

Research on the measurement and evaluation of IR systems, such as:

User-centered evaluation
System-centered evaluation
Beyond Cranfield (e.g., online evaluation, task-based, session-based, multi-turn, interactive search)
Beyond labels (e.g., simulation, implicit signals, eye-tracking and physiological signals)
Beyond effectiveness(e.g., value, utility, usefulness, diversity, novelty, urgency, freshness, credibility, authority)
Synthetic benchmark, datasets, and label generation (e.g., LLM-as-judge and synthetic queries and corpus generation)
Novel methodology for evaluation

IR and Society:

Research on societal implications of IR systems and research, and centering IR research on societal needs:

Fairness, accountability, and transparency
Values, sociotechnical imaginaries, and ethics
Economics, politics, and social justice

Multimodal IR:

Research that bridges the domain of multimedia and IR, such as:

Multimedia search
Multimedia recommendation

Domain-specific Applications:

Research on domain-specific IR problems and challenges, such as:

Local and mobile search
Social search
Search in structured data
Education
Legal
Health
Other applications

IR in Industry:

Open problems and challenges in industry, from industry research to production.

Innovative approaches used in deployed systems and products, and domain-specific challenges are welcome.
Position papers on the current and future state of IR in practice, and the role IR could play in shaping the next generation of information systems.
Role of search, Generative AI & IR in the creator economy (e.g. short video platforms, audio platforms) & marketplaces (e.g. delivery services, hospitality industry, crowdfunding platforms, retail platforms, rentals).
System design case studies from industry practitioners, identifying best practices and design principles for learning systems.
Evaluation in production. Metrics and measurement techniques are used at scale to understand the performance of industrial systems. Success in achieving offline/online evaluation consistency.
Complex user interaction modeling in real-world situations.
Trust and safety: Combating misinformation spread; Building privacy-preserving retrieval systems; Algorithmic responsibility & fairness.
Large-scale systems and models in practice (e.g., foundation models and agentic systems)

Call for Papers