Call for Papers


Important Dates

:loudspeaker: The submission deadline is extended to October 4!

  • Submission Begins: September 1, 2023
  • Submission Deadline: October 1, 2023 October 4, 2023 (11:59pm, anywhere on earth)
  • Notification of Acceptance: October 27, 2023
  • Camera-ready papers due: November 9, 2023
  • Workshop Date: December 15, 2023


Topics of Interest

Centering on “instructions,” we invite submissions covering various topics, including but not limited to the list below:

  • Modeling: algorithms and pipelines for learning from instructions and human feedback; designing training objectives and rewards; training and inference efficiency
  • Data Collection: crowd-sourcing; synthetic data generation; data democratization
  • Evaluation and Oversight: effective and reliable oversight over existing models; enforcing guardrails and guarantees for model behaviors; interpretability and analysis
  • Engineering and Open-sourcing: best practice in training, evaluation and deployment; open-sourcing efforts; openness and reproducibility
  • Applications: long-context, multi-round and personalized instruction-following models
  • Multimodal and Multidisciplinary: instruction following models for computer vision, robotics, games, art, etc.
  • Limitations, Risks and Safety: bias and fairness; factuality and hallucination; safety concerns arising from instruction-following models
  • Other adjacent research topics (e.g., in-context learning, prompting, multi-task learning) that enable better responses to instructions in dynamic environments


Guidelines

  • Paper submission is hosted on OpenReview.
  • We welcome papers up to 9 pages (max), not including references or appendix.
    • Please use the provided LaTex template (zip, overleaf) for your submission.
    • The paper should be anonymized and uploaded to OpenReview as a single PDF.
    • You may use as many pages of references and appendix as you wish, but reviewers are not required to read the appendix.
    • We welcome 4-page extended abstract submissions.
  • This is a non-archival workshop. No submission will be indexed nor have archival proceedings.
    • Accepted papers will appear on the workshop website.
    • They will also be available on OpenReview and NeurIPS virtual site.
    • We accept submissions that are under review at other venues (e.g., ICLR 2024), as long as this does not violate the dual-submission / anonymity policy of the other venue.
  • The review process will be double-blind.
  • We will announce the best paper award at the workshop!