Large language models (LLMs) are increasingly deployed in real-world applications, raising urgent concerns about the values they encode, reflect, and prioritize. While value alignment has become a central topic in AI research, existing studies have largely focused on generic safety or alignment to a single core value (i.e., value monism), leaving the challenge of pluralistic value alignment underexplored. In practice, human values are diverse and context-dependent. Building LLMs that can recognize, reason about, and align with pluralistic values is therefore both a technical and societal challenge.
The First Workshop on Pluralistic Value Alignment of LLMs (PlurVA-LLM) aims to provide a dedicated venue for advancing research on this emerging topic. The workshop will bring together researchers from NLP, machine learning, AI safety, social science, philosophy, and related fields to discuss the foundations, methods, evaluation, and applications of pluralistic value alignment in LLMs.
We welcome submissions on topics including, but not limited to:
The workshop will also host a shared task on evaluating LLMs' value alignment and normative reasoning across adversarial, daily, and principle-driven settings.
We invite submissions to both archival and non-archival tracks.
Long papers (up to 8 pages) and short papers (up to 4 pages), with unlimited pages for references. Submissions can be new papers (double-anonymous review) or papers previously reviewed through ARR.
Accepted archival papers may use one additional page in the camera-ready version and will be published in the ACL Anthology. Previously published work is not eligible for this track.
Two non-archival options—both include a workshop presentation but are not published in the ACL Anthology.
Extended abstract. 2–4 pages plus up to 2 pages of references. Suitable for position papers and early-stage work that benefits from peer feedback. This track uses the same double-anonymous review process as archival submissions.
Previously published or accepted work. For work already reviewed, published, or accepted elsewhere. Include venue or journal information and an archived link if available. Review focuses on fit to the workshop theme; no page limit; anonymization is not required.
Accepted papers in both non-archival tracks are invited for workshop presentation, but will not be published in the ACL Anthology.
Dual submission is permitted: papers that are under review at other venues may be submitted, provided that this is disclosed at the time of submission. If a paper is accepted both here and elsewhere, authors may choose to move it to the non-archival track upon acceptance.
PlurVA-LLM offers three submission routes, each with its own deadline, timeline, and submission link. Details are provided below. Submission links and additional timeline information will be announced shortly.
This route is for new work not published elsewhere. Submissions will undergo full peer review by the program committee. Authors may choose either the archival or non-archival submission type.
Both long and short paper submissions should follow all ACL paper submission requirements.
This route is for papers reviewed through ACL Rolling Review (ARR) that have received meta-reviews by October 11th, 2026. ARR reviews will be considered in the decision, together with the paper's fit to the workshop. Authors may choose either the archival or non-archival submission type.
This route is for work already accepted or published elsewhere and submitted for non-archival presentation at the workshop. Submissions should include the paper, the publication venue or journal, and a link to the archived version, if available.