The NAACL 2027 System Demonstration Program Committee invites proposals for the Demos Track. The goal of the demonstration program is to highlight cutting-edge technologies and tools that have practical value and potential impact.

We welcome submissions from academic researchers, industry practitioners, and open-source contributors. The demonstration track showcases systems whose value has been empirically validated, not just claimed. Strong submissions provide clear evidence of one or more of the following:

  • User studies or human evaluations with the intended target audience
  • Real-world deployment with documented usage (e.g., active users, adoption metrics, testimonials)
  • Systematic evaluation against baselines or existing tools
  • Novel technical contributions whose impact is measurable Building a functional prototype has become significantly easier in the era of AI coding assistants. As a result, the mere existence of a working system, however polished the interface or capable of the underlying models, is not sufficient for acceptance. Submissions whose primary contribution is “vibe coding” a demo, wrapping existing APIs, or assembling off-the-shelf models without substantive technical contribution, thoughtful design grounded in domain expertise, or rigorous evaluation will not be accepted.

Accepted demonstrations will be published in a companion volume of the NAACL 2027 conference proceedings. At least one of the authors is expected to present a live demo during a demo session at NAACL 2027 in San Francisco, with an accompanying poster. Please note that the Demonstrations Program is not intended for commercial sales or marketing. Such activities should be directed to the Exhibit Program instead.

Topics of Interest

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. We particularly welcome submissions that address real-world needs and demonstrate positive societal impact. 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 analysis, interpretability, demonstration or evaluation
  • Software supporting learning or education
  • NLP systems for social good and public interest (e.g., accessibility, healthcare, low-resource languages, digital inclusion, civic engagement, misinformation and fact-checking)
  • Tools for data visualization and annotation
  • Tools for model inspection
  • Development tools

Important Dates

Submission portal opens November 1, 2026
Paper submission deadline December 4, 2026
Notification of acceptance February 10, 2027
Camera-ready submission March 3, 2027
Main conference June 1–5, 2027


All deadlines are 11:59 p.m. UTC -12h (anywhere on earth). Note that there is no rebuttal stage.

Best Demo Award

The NAACL 2027 conference will feature a Best Demo Award, recognizing the most outstanding demonstration. It will be judged according to the innovation, the contribution and the completeness of the live demo system.

Submission Guidelines

Paper submission is electronic, using the OpenReview conference management system.

Note: New OpenReview profiles created without an institutional email address may take up to two weeks to be activated due to moderation. Authors are strongly encouraged to create their OpenReview profiles well in advance of the submission deadline.

The submission process is single-blind (i.e., the submission should not be anonymous, but the reviewers will be anonymous) and must include the following:

A Paper

The accompanying paper for the demonstration should outline the design of the system and provide enough technical details to evaluate 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).

The paper should address the following questions:

  • What problem does the system solve?
  • Why is the system important, and what impact does it have?
  • What is novel about the system’s approach or technology?
  • Who is the target audience?
  • How does the system work?
  • How does it compare to existing systems?
  • How is the system licensed?
  • How was the system evaluated, and were user studies or human evaluations conducted?

Note that submissions that fail to provide any form of evaluation will be desk rejected.

Papers should be no more than 6 pages in length (longer submissions will be desk rejected). An unlimited extra space is allowed for an optional ethics/broader impact statement and references. Appendices are permitted but limited to 2 pages (note the difference to main track papers). We follow the ACL policy on publication ethics and any use of generative AI tools and technologies to create content, whether to support research, build the demo or in writing, should be appropriate and should be fully disclosed in the Acknowledgements section - for instance, “The interface shown in Figure 4 was developed with Claude Code.”

Accepted papers will receive one additional page to address reviewers’ feedback.

Submissions must adhere to the official NAACL 2027 style guidelines and be submitted as PDF files. Style files should meet the requirements of the NAACL main conference. Submissions must be original and unpublished, as NAACL 2027 proceedings are archival. Any submissions that do not follow these guidelines or page limits will be desk rejected.

A Demonstration Video

A short screencast video (up to 2.5 minutes) that demonstrates the system is required, together with your paper submission. This video will be used for evaluation but will not be published unless requested. For demos that can be presented on a screen, a video with audio narration is preferred. If this is not possible, a video showing user interaction with the system is acceptable. Production quality is not a major concern, and we encourage authors to simply create screencasts with minimal to no editing. Authors are encouraged to include captions or narration to make the video accessible. We encourage publishing your video on platforms like YouTube, with a link included in the paper, or submitted 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 must be provided. Submissions that do not provide links will be desk rejected. Exceptions will only be made if sharing a link is clearly impossible (e.g., when specific hardware is required). In such cases, authors must clearly explain why a link cannot be provided.

Multiple Submission Policy

We adhere to the Multiple Submission Policy of the CFPs of the NAACL 2027 main conference. During the review process at NAACL 2027, papers cannot be submitted to other conferences, workshops, or journals. This includes all refereed and archival venues (e.g., IJCAI, ACL workshops), as well as the ARR.

We will not consider any submissions that overlap substantially in content or results with papers being reviewed or already published elsewhere. Authors submitting multiple papers to the NAACL 2027 System Demonstrations Track must ensure that their submissions are distinct, with no significant overlap in content or results (>25%). Any violation of this policy will result in desk rejection.

Reviewing Policy

Reviewing will be single-blind, meaning that authors do not need to conceal their identity. The paper should include the authors’ names and affiliations. Self-references are also allowed.

Reviewers are expected to interact with the provided live demo or installable package as part of their evaluation. Reviewers may consult with area chairs if a demo is inaccessible during the review period.

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 NAACL 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. Please read the ethics FAQ (shared with the main conference) for more guidance on some problems to look out for and key concerns to consider in relation to the code of ethics.

Contact

For Questions, please contact: naacl-2027-demo-chairs@googlegroups.com

Kun Qian, Adobe, USA
Sowmya Vajjala, National Research Council, Canada
NAACL 2027 Demo Chairs