19th International Natural Language Generation Conference INLG 2026

We invite the submission of long and short papers, as well as system demonstrations, related to all aspects of Natural Language Generation (NLG), including data-to-text, concept-to-text, text-to-text and vision-to-text approaches. Accepted papers will be presented as oral talks or posters.

The event is organized under the auspices of the Special Interest Group on Natural Language Generation (SIGGEN)
of the Association for Computational Linguistics (ACL).

The event will be held from October 17 to October 21, 2026. INLG 2026 will be hosted by Utrecht University in Utrecht, the Netherlands. The conference will be taking place before EMNLP (in Budapest, Hungary, from October 24th to October 29th, 2026).

**Important dates**

All deadlines are Anywhere on Earth (UTC-12):

* Regular paper submission deadline: July 15, 2026.
* System demo paper submission deadline: July 15, 2026.
* ARR commitment to INLG deadline: August 5, 2026.
* Notification: August 15, 2026
* Non-archival submission deadline: August 22, 2026.
* Camera ready: September 7, 2026
* Conference: October 17 - October 21, 2026


**Topics**

INLG 2026 solicits papers on any topic related to NLG. General topics of interest include, but are not limited to:


* Large Language Models (LLMs) for NLG
* Evaluation and error analysis of NLG systems
* Explainability and Trustworthiness of NLG systems
* Generalizability of NLG systems
* Bias and fairness in NLG systems
* Affect/emotion generation
* Analysis and detection of automatically generated text
* Cognitive modeling of language production
* Computational efficiency of NLG models
* Content and text planning
* Corpora and resources for NLG
* Ethical considerations of NLG
* Grounded language generation
* Lexicalisation
* Multimedia and multimodality in generation
* Natural language understanding techniques for NLG
* NLG and accessibility
* NLG in speech synthesis and spoken language models
* NLG in dialogue systems and chatbots
* NLG for human-robot interaction
* NLG for low-resourced languages
* NLG for real-world applications
* Paraphrasing, summarization and translation
* Personalisation and variation in text
* Referring expression generation
* Storytelling and narrative generation
* Sub-tasks of the classic
NLG pipeline
* NLG architectures

**Submissions**

This year’s INLG will have two tracks: an archival track where papers will be published in the ACL Anthology, and a non-archival track for works in progress and papers published elsewhere. Three kinds of papers can be submitted for the archival track:


* Long papers are most appropriate for presenting substantial research results and must not exceed eight (8) pages of content, plus unlimited pages of ethical considerations, supplementary material statements, and references. The supplementary material statement provides detailed descriptions to support the reproduction of the results presented in the paper (see below for details). The final versions of long papers will be given one additional page of content (up to 9 pages) so that reviewers' comments can be taken into account.
* Short papers are more appropriate for presenting an ongoing research effort and must not exceed four (4) pages, plus unlimited pages of ethical considerations, supplementary material statements, and references. The final versions of short papers will be given one additional page of content (up to 5 pages) so that reviewers' comments can be taken into account.
* Demo papers should be no more than two (2) pages, including references, and should describe implemented systems relevant to the NLG community. It also should include a link to a short screencast of the working software. In addition, authors of demo papers must be willing to present a demo of their system during INLG 2026.
* Next to the standard paper types (surveys, experiments, resource papers, position papers), we also welcome
squibs: papers that present an empirical or theoretical issue without necessarily providing a solution.

Through the non-archival track, we hope to foster more discussion on current trends in NLG, and to offer a space for researchers to obtain feedback on their current projects. For this track, we welcome two kinds of submissions:


* Papers published elsewhere. These may be published either in a journal or at another conference, and should be relevant to the INLG audience.
* Work in progress. These may be papers about completed work that has not yet been published or preliminary results that merit discussion at the conference. Submissions should consist of a title and a short abstract (max. 300 words).
* Submissions for the non-archival track will undergo a light review process (assessing the relevance of the submission for INLG), and accepted works will be presented as posters.

**Format**

Submissions should follow ACL Author Guidelines and policies for submission, review and citation, and be anonymised for double blind reviewing. Please use ACL style files; LaTeX style files and Microsoft Word templates are available at: https://acl-org.github.io/ACLPUB/formatting.html.

Authors must honour the ethical code set out in the ACL Code of Ethics. If your work raises any ethical issues, you should include an explicit discussion of those issues. This will also be taken into account in the review process.

Authors are strongly encouraged to ensure that their work is reproducible; see, e.g., the following
reproducibility checklist. Papers involving any kind of experimental results (human judgments, system outputs, etc) should incorporate a data availability statement into their paper. Authors are asked to indicate whether the data is made publicly available. If the data is not made available, authors should provide a brief explanation why. (E.g. because the data contains proprietary information.) A statement guide is available on the INLG 2026 website.

**Awards**

INLG 2026 will present several awards to recognize outstanding achievements in the field. These awards are:


* Best Long Paper Award: This award will be given to the best long paper submission based on its originality, impact, and contribution to the field of NLG.
* Best Short Paper Award: This award will be given to the best short paper submission based on its originality, impact, and contribution to the field of NLG.
* Best Demo Paper Award: This award will recognize the best demo paper submitted to the conference. This award considers not only the paper's quality but also the demonstration given at the conference. The demonstration will play a significant role in the judging process.
* Best Evaluation Award: The award was introduced at INLG 2024. This award is designed to honour authors who have demonstrated the most comprehensive and insightful analysis in evaluating their results. This award aims to highlight papers where the authors have gone the extra mile in providing a thorough and detailed analysis of their results, offering a nuanced understanding of their findings.


**Communication Channels**

* Website: https://2026.inlgmeeting.org/
* Bluesky: https://bsky.app/profile/siggen.bsky.social
* LinkedIn: https://www.linkedin.com/company/siggen/
* Mastodon: https://fediscience.org/@siggen_acl
* X (formerly Twitter): x.com/inlgmeeting


Program Chairs: Emiel van Miltenburg (Tilburg University), Laura Perez-Beltrachini (University of Edinburgh), Guanyi Chen (Central China Normal University)