Paper Submission Guidelines

How should the paper be structured? (4 pgs maximum + unlimited references)

1. Abstract

Brief summary of your paper in a few sentences.

2. Introduction 

• Task description and importance; mention language(s) covered; cite task overview paper

• Your main system strategy

• Key findings, ranking, challenges discovered; include code URL if available (Highly recommended)

3. Background

• Summarize task setup: input/output types (with examples)

• Dataset details: language, genre, size

• Tracks participated in (if applicable)

• Cite relevant related work showing your contribution's novelty

4. System Overview 

• Key algorithms and design decisions

• Resources used beyond provided training data

• How you addressed task challenges

• Include equations/pseudocode for novel approaches

• Provide concrete algorithm examples

• For multiple systems, clearly distinguish each configuration

5. Experimental Setup

• Data split usage (train/dev/test)

• Preprocessing and hyperparameter details for replication

• External tools/libraries (with versions and URLs)

• Task evaluation metrics summary

• Put detailed implementation in Appendix if space-limited

6. Results

• Quantitative findings: Official metrics performance and ranking

• Analysis: Ablations, comparisons, design decisions impact

• Error analysis: System mistakes, confusion matrices, error types, make sure to provide some examples.

• Clearly mark which data split used for each analysis

• Distinguish official vs. post-submission results

7. Conclusion

Summary of system, limitations, results, and future work directions.

8. Acknowledgments

Thank contributors, grants, anonymous reviewers.

9. Appendix

Low-level details for replication that aren't essential for understanding main concepts.

Formatting Requirements ⚠️

Templates and Style

• Must use: Official EMNLP 2025 (ACL) style templates (LaTeX or Word)

• Download from: https://github.com/acl-org/acl-style-files

• Follow: General "*ACL" conference formatting guidelines

• Do NOT: Modify style files or use templates from other conferences to avoid the paper rejection

Consequences

• Non-conforming submissions (wrong paper size, margins, font size) will be rejected without review

Key Principles

Focus on:

• Replicability: Provide all necessary implementation details

• Analysis: Emphasize results over rankings; include multiple runs and ablations

• Clarity: Brief task outline (avoid duplicating task paper); use placeholder citations initially

Required elements:

• Cite task overview paper

• Follow EMNLP templates exactly

• Use title format: <Team Name> at <Task Name>: <Your Contribution>

For popular algorithms: Citation suffices (no need for full mathematical details)

• Space management: Move detailed parameters/hyperparameters to Appendix if needed

Where do I submit the paper?

Submissions should be made via OpenReview. Please ensure you have an OpenReview account set up if you have not done so already. The submission link will be provided soon.

 Visit OpenReview here: [OpenReview] https://openreview.net

What are the required citations?

Word Versions

• Alhuzali, H., Alasmari, A., & Alsaleh, H. (2024). MentalQA: An Annotated Arabic Corpus for Questions and Answers of Mental Healthcare. IEEE Access. 

• Abu Daoud, M., Abouzahir, C., Kharouf, L., Al-Eisawi, W., Habash, N., & Shamout, F. E. (2025). MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks. arXiv e-prints, arXiv-2505.

• Coming Soon: Shared Task Overview Paper

Overleaf BibText version

Mental QA

@article{alhuzali2024mentalqa,

  title={MentalQA: An Annotated Arabic Corpus for Questions and Answers of Mental Healthcare},

  author={Alhuzali, Hassan and Alasmari, Ashwag and Alsaleh, Hamad},

  journal={IEEE Access},

  year={2024},

  publisher={IEEE}

}

MedArabiQ

@article{abu2025medarabiq,

  title={MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks},

  author={Abu Daoud, Mouath and Abouzahir, Chaimae and Kharouf, Leen and Al-Eisawi, Walid and Habash, Nizar and Shamout, Farah E},

  journal={arXiv e-prints},

  pages={arXiv--2505},

  year={2025}

}

Coming Soon: Shared Task Overview Paper

@article{

...

}

Guidelines for Participation

Q: Who can participate in shared tasks? 

A: Anyone who wants to can participate, either independently or by forming a team.

Q: Is there a fee to participate in a task? 

A: No, participation is completely free but at least one team member should pay to register for the conference.

Q: How can I sign up to participate in a task? 

A: Please see instructions on the website for the task (e.g., on CodaLab or other evaluation platforms).

Q: Can I participate in multiple shared tasks (separate competitions)? 

A: Yes, you can participate in multiple different tasks.

Q: Can I participate in multiple teams under the same shared task (same competition)? 

A: This depends on the task. Check with the task organizers to see whether they allow an individual to be part of multiple teams within the task.

Q: What does "evaluation period" mean? 

A: The evaluation period is the time window in which the official part of each task competition takes place. Task organizers will release evaluation data to participants at the beginning of the evaluation period, and system outputs will be due before the end of the evaluation period.

Q: How many runs can be submitted for a task? 

A: This depends on the task. Task organizers often specify how many submissions by each team will be evaluated. Contact your task organizers if these details are not already stated on the task webpage.

Q: Where can I find datasets from past shared tasks? 

A: Task datasets are distributed by task organizers. Check the task website or contact the organizers. Many recent tasks archive their datasets on platforms such Github.

Q: Do I need to write a paper? 

A: Yes, if you register and request the dataset, you agree to submit a paper. It's not just encouraged—it's a binding commitment you make when receiving the data.

Q: What happens if I register but don't submit a paper? 

A: This is strictly prohibited. You agree to register and submit a paper when requesting the dataset. Abandoning the task after receiving data may result in banning participants from future participation.

Q: What is the paper format? 

A: Shared task papers must follow the format for  short papers at ArabicNLP 2025. Papers must follow official EMNLP (ACL) LaTeX or Word templates, be up to 4 pages (excluding unlimited references), check the dedicated paper submission guidelines URL below for more details.

https://github.com/acl-org/acl-style-files

Q: How should the paper title be formatted? A: Use this format: <Team Name> at <Shared Task Name>: <Title of the work> Example: "Scholarly at XYZ Shared Task: LLMs in Detection for Identifying Manipulative Strategies"

Q: Must I cite the task overview paper? 

A: Yes, each team is required to cite the shared task overview paper in their system paper.

Q: Must someone from my team attend the conference? 

A: Yes, at least one of the shared task team members should register and attend the conference.

Q: Must papers be presented at the conference? 

A: Yes, all accepted papers must be presented at the conference (in-person or virtual). Papers without at least one presenting author registered by the early registration deadline may be subject to desk rejection.

Q: Do I need an OpenReview account? 

A: Yes, all participants and organizers are required to create an OpenReview account.

Q: Are the papers anonymous? 

A: No, shared task papers (both system and overview papers) are not anonymous.

Q: What happens if I exceed the page limit or miss required sections? 

A: Submissions that exceed length requirements will be desk rejected.

Q: Will I need to review other papers?

 A: Yes, shared task teams are expected to serve as reviewers, and their reviews will be checked by one member of the shared task organizers.

Q: Can I post my paper on arXiv? 

A: Yes, authors are free to submit papers to arXiv at any time. Since papers are not anonymous, this won't interfere with the review process.

Q: Can I make changes for the camera-ready version? 

A: No additions/revisions or name changes are allowed after the review period for the camera-ready version.

Q: What if my research raises ethical concerns? 

A: If your research raises ethical considerations (e.g., potential for misuse), these should be discussed in the paper.

Q: Should I release my code? 

A: You are highly encouraged to release the code or data used and include the URL in the paper. This promotes reproducibility.

Q: My question isn't answered here. Who should I contact? 

A:

• For task-specific questions: Consult the task website and contact task organizers

• For workshop logistics: Contact the shared task organizers

• For OpenReview technical issues: Contact OpenReview support