The EMNLP 2025 System Demonstration Program Committee invites proposals for the Demonstrations Program. Demonstrations may range from early research prototypes to mature production-ready systems. Publicly available open-source or open-access systems are of special interest. We additionally strongly encourage demonstrations of industrial systems that are technologically innovative given the current state of the art of theory and applied research in natural language processing.
Areas of interest include all topics related to theoretical and applied natural language processing, such as (but not limited to) the topics listed on the main conference website. Submitted systems may be of the following types: * Natural language processing systems or system components * Application systems using language technology components * Software tools for natural language processing research * Software for demonstration or evaluation * Software supporting learning or education * Tools for data visualization and annotation * Tools for model inspection * Development tools Papers describing accepted demonstrations will be published in a companion volume of the EMNLP 2025 conference proceedings. We require at least one of the authors to present a live demo during a demo session at EMLP 2025, with an accompanying poster. Please note: Commercial sales and marketing activities are not appropriate in the Demonstrations Program and should be arranged as part of the Exhibit Program. Important Dates: Paper submission deadline: Friday, July 4, 2025 Notification of acceptance: Tuesday, September 9, 2025 Camera ready submission: Friday, September 19, 2025 Main Conference: November 5-9, 2025 All deadlines are 11.59 pm UTC -12h (“anywhere on Earth”) Note that there is no rebuttal stage. Submission Guidelines: Submissions must include the following: * A Paper * A paper submitted to accompany a demonstration should outline the design of the system and provide sufficient details to allow the evaluation of its validity, quality, and relevance to natural language processing. * Technical details of the system are required, including visual aids (e.g., screenshots, snapshots, or diagrams). A paper can do this by addressing the following questions: * What problem does the proposed system address? * Why is the system important and what is its impact? * What is the novelty in the approach/technology on which this system is based? * Who is the target audience? * How does the system work? * How does it compare with existing systems? * How is the system licensed? * How was the system evaluated? Were user studies/human evaluation experiments conducted? Note that this year, submissions that do not report any form of evaluation may be desk rejected. Paper submission is electronic, using the OpenReview conference management system. The submission site can be found at https://openreview.net/group?id=EMNLP/2025/System_Demonstrations Submissions can contain up to 6 pages (longer submissions will be desk rejected), plus unlimited extra space for an optional ethics/broader impact statement and also unlimited space for references and informative appendices. Accepted papers will be given one additional page of content, so that reviewers’ comments can be taken into account. Submissions must conform to the EMNLP 2025 official style guidelines and they must be in PDF format. Style files should meet the requirements of the EMNLP main conference. Submissions need to describe original, unpublished work, as publication in EMNLP will be archival. Any papers that do not follow the official style guidelines and page limits will be desk rejected. A Demonstration Video A short (at most 2.5 minutes) screencast video demonstrating the system together with your paper submission. This screencast will be used to evaluate the paper, but won’t be published unless requested. For demos that can be presented on a screen, a screencast with audio narration is the most suitable format. If this is not feasible, a video showcasing user interaction with the system may be utilized. Production quality is not a priority, so we encourage to simply create a screencast of the software being demoed with minimal to no editing. We encourage publishing your video on YouTube or a similar site and including the link in your paper. If you prefer not to upload the video publicly, please submit it as supplementary material in MPEG4 format when you submit your paper through the official website. Live Demo Website or Installable Package A link to a live demo website; or a link to a downloadable installation package of the demo. Note that this is a strict requirement enforced this year, and submissions that do not provide links will be desk rejected. Exceptions will be made only in cases where sharing a link is clearly impossible, such as when special hardware is required. In such cases, authors must clearly state why a link cannot be provided. Multiple Submission Policy We follow the Multiple Submission Policy of the CFPs of the EMNLP 2025 main conference. The paper cannot be submitted elsewhere, while in review at EMNLP 2025. This policy covers all refereed and archival conferences and workshops (e.g., NeurIPS, ACL workshops), as well as ARR. In addition, we will not consider any paper that overlaps significantly in content or results with papers that will be (or have been) published elsewhere. Authors submitting more than one paper to the EMNLP 2025 System Demonstrations Track must ensure that their submissions do not overlap significantly (>25%) with each other in content or results. Reviewing Policy Reviewing will be single-blind, so authors do not need to conceal their identity. The paper should include the authors’ names and affiliations. Self-references are also allowed. Ethics Policy Authors are required to honor the ethical code set out in the ACM Code of Ethics. The ethical impact of our research, the use of data, and potential applications of our work have always been an important consideration, and as artificial intelligence is becoming more mainstream, these issues are increasingly pertinent. We ask that all authors read the code, and ensure that their work is conformant to this code. We reserve the right to reject papers on ethical grounds, where the authors are judged to have operated counter to the code of ethics, or have inadequately addressed legitimate ethical concerns about their work. Authors will be allowed extra space after the 6th page for a broader impact statement or other discussion of ethics. The EMNLP demonstration review form will include a section addressing these issues and papers flagged for ethical concerns by reviewers will be further reviewed by an ethics committee. Note that an ethical considerations section is not required, but papers working with sensitive data or on sensitive tasks that do not discuss these issues will not be accepted. Conversely, the mere inclusion of an ethical considerations section does not guarantee acceptance. In addition to acceptance or rejection, papers may receive a conditional acceptance recommendation. Camera-ready versions of papers designated as conditional accept will be re-reviewed by the ethics committee to determine whether the concerns have been adequately addressed. Demonstration Co-chairs: Ivan Habernal, RC Trust; Ruhr University Bochum Peter Schulam, Amazon AGI Jörg Tiedemann, University of Helsinki Contact: [email protected]<mailto:[email protected]>
