2nd CFP (PlurVA-LLM @ AACL 2026): The First Workshop on Pluralistic Value Alignment of LLMs

1. Call for papers

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.

2. Topics of interest

We welcome submissions on topics including, but not limited to:

1. Theoretical foundations and formalizations of pluralistic value alignment
2. Alignment methods for pluralistic values in LLMs
3. Benchmarks and evaluation protocols for pluralistic value alignment
4. Human-AI collaboration for constructing and curating value-sensitive datasets
5. Interpretability and analysis of value alignment in LLMs
6. Pluralistic value alignment in downstream applications and real-world deployment
7. Multilingual, multicultural, and low-resource perspectives on value alignment
8. Pluralistic value alignment in multimodal models and systems

The workshop will also host a shared task on evaluating LLMs' value alignment and normative reasoning across adversarial, daily, and principle-driven settings.

3. Submission tracks

We invite submissions to both archival and non-archival tracks.

• Archival track
  • Long papers up to 8 pages and short papers up to 4 pages, with unlimited
    pages for references.
  • Submissions can be new papers using 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.
• Non-archival tracks
  • Two non-archival options are available. 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.

4. Organizers
Deyi Xiong, Tianjin University
António Branco, University of Lisbon
Hongming Zhang, Macau University of Science and Technology
Yue Dong, University of California, Riverside
Benyou Wang, The Chinese University of Hong Kong, Shenzhen
Wenxuan Zhang, Singapore University of Technology and Design (SUTD)
Li Zhou, The Chinese University of Hong Kong, Shenzhen
Jingting Zheng, Tianjin University

For questions, please contact plurvallm2026 [at] outlook.com