Co-located with LREC 2026, Palma, Mallorca (Spain)
OVERVIEW
Deliberation is ubiquitous: from navigating divergent interests in everyday personal life to reaching consensus in the political decision making process, deliberation describes the communicative process by which a group of people exchange ideas, weigh different arguments, and ultimately reach mutual understanding. In recent years, deliberative processes have gained momentum and shown to improve everyday and political decision-making. For the first time, technological solutions are maturing to the point that they can be deployed to support deliberation.
The DELITE workshop provides a forum for presenting new advances in technology around deliberation by addressing researchers in Natural Language Processing, human-computer interaction, corpus linguistics, political science and philosophy, as well as stakeholders and domain experts involved in integrating such technology into decision-making processes.
The topic is particularly timely in the age of LLMs and collective intelligence, which has heightened the awareness of the public to the potentials and drawbacks of language technology.
While LLMs are transforming the way that much AI research is carried out, it is becoming clear that handling natural argumentation, particularly the sort of discussion found in deliberative settings, presents deep challenges for LLMs that are not likely to be overcome soon. The complex pragmatic structure of such discussions, the subjectivity of the phenomena involved (emotions, storytelling), nuanced presentation, framing and reframing of ideas, and resolution of differences of opinion all lay many orders of magnitude beyond the current parameterisation spaces of such models.
We view deliberation as an exercise in Collective Intelligence—the enhanced capacity of groups to make decisions due to collaboration and structured interaction. AI systems should augment and never replace human deliberation, by supporting facilitators, providing discussion summaries, and amplify/enact diversity in group decision making processes.
TOPICS OF INTEREST
We welcome submissions that address the gaps facing this nascent field, including the scarcity of data on large-scale deliberation, the need for stakeholder requirements, and the need for technology that fosters trust. Topics include, but are not limited to:
- Deliberation theory in NLP models
- In-domain versus across domain resources
- Integrating language systems into deliberation processes and interfaces
- Technological solutions for online deliberation at scale
- Argument mining for deliberation scenarios
- Visualising language systems results for human sensemaking
- Empirical foundations for evaluation
- Integrating and reflecting on recent advances in LLMs for deliberation scenarios
- Collective Intelligence frameworks for deliberation at scale
- Human-AI collaboration in group decision-making
- Explainability, ethical questions, and addressing bias
APPLICATION AREAS
We welcome submissions from all areas of application, including public policy making, democratic innovations, deliberative democracy, political decision making, citizen engagement and co-creation, intelligence services and military, conflict resolution/mitigation, case analysis in healthcare, legal decision making, and scholarly discourse.
SUBMISSION
DELITE 2026 introduces new submission formats to foster diversity and inclusion, specifically opening the venue to junior researchers and fields where conference papers are not standard (e.g., Social Sciences).
- Standard Papers: Oral and poster presentations of long and short papers.
- Extended Abstracts: A new format designed to be inclusive of researchers from fields where conference papers are not standard (e.g., Social Sciences).
- PhD Project Proposals: A non-archival submission option allowing doctoral students to collect feedback on their research plans without the pressure of a full-fledged publication.
- Non-Archival Reports: Poster presentations of non-archival reports of ongoing projects to serve community building.
Standard papers must describe original (completed or in progress) and unpublished work. These papers can be long (8 pages, excluding references) or short (4 pages, excluding references) and must be anonymized to support double-blind reviewing, i.e., they must not include authors’ names and affiliations and should avoid links to non-anonymized repositories. Standard papers that do not conform to these requirements will be rejected without review.
Nette: What info do we include for the other ones?
Submission of all papers is electronic, using the Softconf START conference management system. Papers must follow the LREC 2026 two-column format, using the supplied official style files. The templates can be downloaded from the Style Files and Formatting page provided on the website. Please do not modify these style files, nor should you use templates designed for other conferences. Submissions that do not conform to the required styles, including paper size, margin width, and font size restrictions, will be rejected without review.
IMPORTANT DATES
Paper submission deadline: TBD
Notification of acceptance: TBD
Camera-ready versions due: TBD
Workshop date: TBD
WORKSHOP ORGANIZERS
- Lucas Anastasiou, The Open University, UK
- Katarina Boland, Heinrich Heine University Düsseldorf, Germany
- Anna De Liddo, The Open University, UK
- Neele Falk, University of Stuttgart, Germany
- Annette Hautli-Janisz, University of Passau, Germany
- Gabriella Lapesa, GESIS Leibniz Institute for the Social Sciences, Germany & Heinrich-Heine University of Düsseldorf, Germany
- Julia Romberg, GESIS Leibniz Institute for the Social Sciences, Germany
PROGRAM COMMITTEE
TBD
CONTACT
lucas.anastasiou@open.ac.uk
The LRE 2026 Map and the “Share your LRs!” initiative
When submitting a paper from the START page, authors will be asked to provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research. Moreover, ELRA encourages all LREC authors to share the described LRs (data, tools, services, etc.) to enable their reuse and replicability of experiments (including evaluation ones)”.