Full Papers

Table of Contents

ACM Conversational User Interfaces – CUI (pronounced “coo-ee”) was founded in 2018 to bring together researchers and practitioners from a wide range of disciplines examining the design of speech and language technologies. In late 2022, CUI joined SIGCHI, the Association for Computing Machinery Special Interest Group on Computer-Human Interaction. 

The CUI 2026 conference theme is “Conversational AI: Agency and Identities!”. The conference seeks contributions from a broad range of disciplines, including human-computer interaction, computer science, engineering, speech technology, linguistics, psychology, cognitive sciences, sociology, and other cognate disciplines that advance fundamental and applied research in conversational user interfaces. We also encourage the submission of high-quality replication studies in addition to well-designed studies with null results.

Topics relevant to the conference include, but are not limited to:

  •     Voice user experience
  •     Speech Interfaces
  •     Text-based conversational interfaces
  •     Chatbots
  •     Speech synthesis
  •     Speech recognition
  •     Context-aware dialogue management
  •     Conversational search
  •     Methods for conversational user interface development and evaluation
  •     Multimodal interaction involving speech, text or other language based interfaces
  •     Natural language processing and understanding related to the above
  •     Ethical and privacy considerations related to the above
  •     Large Language Models (LLMs)

Papers must describe original work that has not been previously published, not accepted for publication elsewhere, and is not simultaneously submitted or currently under review in another journal or conference (including the other tracks of ACM CUI 2026).

Each submission will require the author(s) to volunteer to complete three reviews of other papers.

Important Dates

Deadline typeDate
Submission AbstractThu, February 26, 2026
Submission Full PaperThu, March 5 2026
Acceptance NoticeThu, May 7 2026
Camera-Ready in PCSThu, May 21 2026
eRights completedThu, May 28 2026
TAPS processing completedThu, June 4 2026
* all Deadlines are AoE as well as preliminary and may be subject to change. Check your local time in AoE.

Abstracts Submission

Please be aware that, similar to last year, we require all full papers to submit an abstract and metadata about the paper prior to the paper submission deadline. Papers that did not submit the abstract on time will not be accepted.

In addition, the abstract, title, and list of authors’ information that is submitted at that time must be complete. Submissions for which it is obvious that the information submitted by the abstract deadline is merely a placeholder or incomplete will be deleted.

Format and Submission

Full papers are 6,000-10,000 words (including figures, tables, proofs, appendixes, and any other content excluding references and acknowledgments). Submissions above 10,000 or below 6,000 words will require justification for the length in relation to the contribution. Papers whose lengths are incommensurate with their contributions may be rejected.

All papers will be reviewed by multiple external reviewers. Another programme committee member will lead the reviewing process, write a meta review, and later check on the paper for final acceptance if it got conditionally accepted (all accept decisions are conditional).

You must use the ACM LaTeX or Word templates to prepare your submission. 

The correct template for initial submissions is one of:

We encourage the use of LaTeX and the official ACM template on Overleaf. LaTeX users must employ the following document class for submission: \documentclass[manuscript,screen,review,anonymous]{acmart}. 

Word users must use the one-column submission template and should be prepared to submit to TAPS approximately one week earlier than the stated camera-ready deadline.

ACM’s CCS concepts and keywords are not required for submission and peer review but are required if your paper is accepted and published by the ACM.

ACMs New Open Access Publishing Model

Starting January 1, 2026, ACM will fully transition to Open Access. All ACM publications, including those from ACM-sponsored conferences, will be 100% Open Access. Authors will have two primary options for publishing Open Access articles with ACM: the ACM Open institutional model or by paying Article Processing Charges (APCs). With over 2,600 institutions already part of ACM Open, the majority of ACM-sponsored conference papers will not require APCs from authors or conferences (currently, around 76%).

Authors from institutions not participating in ACM Open will need to pay an APC to publish their papers, unless they qualify for a financial or discretionary waiver. To find out whether an APC applies to your article, please consult the list of participating institutions in ACM Open and review the APC Waivers and Discounts Policy. Keep in mind that waivers are rare and are granted based on specific criteria set by ACM.

Understanding that this change could present financial challenges, ACM has approved a temporary subsidy for 2026 to ease the transition and allow more time for institutions to join ACM Open. The subsidy will offer:

  • $250 APC for ACM/SIG members
  • $350 for non-members

This represents a 65% discount, funded directly by ACM. Authors are encouraged to help advocate for their institutions to join ACM Open during this transition period. This temporary subsidized pricing will apply to all conferences scheduled for 2026, including CUI.

New ACM Publication Policies

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 (https://www.acm.org/publications/policies/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.

Accessibility

Paper submissions are expected to follow the SIGCHI Guide to an Accessible Submission. 

When preparing figures, make sure to rely not only on colour to mark information. Authors are expected to provide a text description for all figures. Tables, equations and quotes should be inserted as marked-up elements, not as images. 

Anonymization

The CUI papers review process is based on reviewing where the identities of both the authors and reviewers are kept hidden (but 1ACs know these details). Authors are expected to remove author and institutional identities from the title and header areas of the paper, as noted in the submission instructions (n.b., changing the text color of the author information is not sufficient). Make sure that no description or information that can easily reveal authors’ identities is included in the submission (e.g., too detailed descriptions of where user studies were conducted, where authors received IRB approvals, or figures that include faces of authors). Authors should also remove any information in the acknowledgements section that reveals authors or the institution (e.g., specific supporting grant information). Also, please make sure that identifying information does not appear in the document’s metadata (e.g., the ‘Authors’ field in your word processor’s ‘Save As’ dialog box).

Authors are expected to anonymize their identities in the body of the paper, but leave citations to their previous work unanonymized so that reviewers can ensure that all previous research has been taken into account by the authors. Authors are required to cite their own work in the third person, e.g., avoid “As described in our previous work [10], … ” and use instead “As described by Doe et al. [10], …” In cases where anonymization in the context of prior work is especially tricky, please contact the Papers chairs and ask for advice. Note that the use of any references marked “anonymous” is grounds for desk rejection. 

In order to ensure the fairness of the reviewing process, CUI uses a review process where external reviewers do not know the identity of authors, and authors do not know the identity of external reviewers. While publication in public archives (e.g. arXiv) is becoming standard across many fields, authors should be aware that unconscious biases can affect the nature of reviews when identities are known. CUI does not discourage non-archival publication of work prior to or during the review process, but recognizes that complete anonymization becomes more difficult in that context. While reviewers should not actively seek information about author identity, complete anonymization is difficult and can be made more so by publication and promotion of work during the CUI review process.

If a submission contains any element (e.g., text or figures in the full paper document, artifacts, or supplementary materials) that violates the anonymization guidelines, it will be desk rejected. If there are exceptional circumstances, please contact the Paper Chairs as soon as possible (papers@cui.acm.org).

Supplementary Materials

Supplementary materials are not required for a submission. In general, there are three main types of supplemental materials that may be submitted: videos, appendices, and artifacts (e.g., software, hardware, data sets, etc.). Supplementary material may include, for example, questionnaires used as measurements, survey text, experimental protocols, figures of experimental apparatus, tables of supplementary data, source code, and data, all of which can help reviewers assess your work as well as allow other researchers to replicate your work. Note that appendices should never be added to the main document (even if the LaTeX template allows it). Instead, appendices should be submitted as a supplementary material, and will be archived together with the paper in the ACM DL. Any non-video supplementary material should be submitted as a single .zip file, including a README file with a description of the materials.

Reviewers should be able to access the contribution of the paper solely based on the main submission file. That is, the paper submission must stand on its own without the supplementary material. If authors do choose to submit supplementary materials, such materials may not be used to get around the page limit for full paper submissions. Additional experimental analysis, additional results, and lengthy text that clarifies aspects of the full paper submission is not appropriate for an appendix. Any submissions that attempt to use appendices or supplementary materials in general in a manner that violates the page limits will be desk rejected.

All supplementary material must be anonymized. Non-anonymized supplemental materials will result in desk rejection of the entire submission.

Studies with Human Participants

As a published ACM author, 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 (Note: ACM has instituted a new policy on research involving human participants and subjects as of August 15, 2021. Please check the above links if your studies involved human participants and subjects).

To support building a strong evidence base in CUI, and encourage future reproducibility of published work, all submissions involving studies with human participants clearly outline their methodology regardless of the theme they are submitted to, including:

  • If a Wizard-of-Oz paradigm was used, a detailed description of the CUI system, wizard, user, etc. (c.f., Riek 2012, Table 2)
  • If a CUI system was used, a detailed description of the platform and its capabilities.
  • If generative AI models are used, a reflection on their openness (c.f. Liesenfeld et al., 2023)

In addition, studies that involve human participants need to include an ethical approval statement. According to the ACM Publications Policy on Research Involving Human Participants and Subjects, “It is the authors’ responsibility (each author individually and the authors collectively) to comply with and provide evidence of compliance with this Policy. Where local ethical review boards are required, authors are responsible for having their research reviewed and approved by such boards. Authors are also responsible for the overall ethical conduct of their research. All ACM Authors must be prepared to provide documentary evidence to ACM that they have adhered to local ethical and legal standards, as ACM may require documentary evidence of such approval at any time following submission of the Work and prior to or after publication of the Work.” In the case of child users, in addition to consent from legal carers / parents, authors should describe how they obtained the oral assent from minors. Examples of such statements are “the study was approved by our Institutional Review Board” or “the study design, the experiment protocol, and the consent forms received approval from the Ethics Committee of our institution” (note that these statements must be anonymized). Additionally, during paper submission, authors will be asked to declare whether their research involves human participants, and if it does, whether approval from a relevant ethics committee was obtained.

We recognize that some researchers may work in jurisdictions where there is no mandated ethical review, or may not have access to an institutional ethics committee. In such cases, we will follow the ACM’s Policy on Research Involving Human Participants and Subjects, which lists a basic set of standards and practices that a research should follow, and states that “where such research is conducted in countries where no such local governing laws and regulations related to human participant and subject research exist, authors must at a bare minimum be prepared to show compliance with the above detailed principles.” In addition to the declaration mentioned above, the paper submission form contains also an optional question allowing authors to describe additional context related to human participant protection. If additional explanations regarding institutional review are needed, and in particular if no ethics approval was obtained for the research, the authors should answer this question with enough detail to show that their research was done in full compliance with the ethical research principles stated in the ACM Policy.

Policy on Use of ChatGPT or Similar Models for Paper Writing 

Text, images or any material generated from foundation models (LLMs, VLMs etc.), such as ChatGPT, must be clearly marked where such tools are used for purposes beyond editing the author’s own text. Please carefully review the April 2023 ACM Policy on Authorship before you use these tools. The SIGCHI blog post describes approaches to acknowledging the use of such tools and we refer to it for guidance. Note that the LaTeX template will default to hiding the Acknowledgements section while in review mode – please make sure that any LLM disclosure is available in your submitted version for review. While we do not anticipate using tools on a large scale to detect LLM-generated text, we will investigate submissions brought to our attention and desk reject papers where LLM use is not clearly marked.

Furthermore, CUI follows the ACM Policy on Authorship. Please carefully review this policy. Any AI system, including Generative Models, such as ChatGPT, Gemini, or DALL-E, do not satisfy the criteria for authorship of papers and, as such, also cannot be used as a citable source in papers published by ACM. Authors assume full responsibility for content, including checking for plagiarism and veracity of all text.

Desk rejects

Desk rejects are made during the initial checks of submissions to save our reviewers’ time. The main reasons for a desk rejections include:

  • Scope: clearly out of scope for conference (e.g., no relevance to human-computer interaction involving conversational user interfaces or speech and language technology).
  • Anonymization: any violation of the rules detailed in the anonymization guidelines
  • Incomplete submissions: missing submission information (including an obviously placeholder title or abstract, etc.).
  • Formatting issues:
    • paper is breaking the full paper limit (significantly over 10 000 words excluding references);
    • using an incorrect submission template.
  • Other obvious issues, such as paper clearly unfinished, use of foundation models for generating the contents which does not comply with the ACM Policy on Authorship, not written in English, etc.

Contacts

If you have any questions, contact the Program Chairs Justin Edwards (University of Oulu) and Hannah Pelikan (Linköping University) or Paper Chairs Anke Reinschluessel (University of Konstanz), Michal Luria (Center for Democracy & Technology) and Donald McMillan (Stockholm University)