NeurIPS’24 Workshop: Interpretability in Action – Present, Past and Future

The Interpretability in Action: Present, Past and Future workshop at NeurIPS 2024 invites submissions for its three tracks: Regular, Published, and Position papers. The deadline for submissions is August 30, 2024. This workshop aims to bridge classical interpretability research with modern methods for foundation models, fostering discussions on the mathematical foundations, methodology, design, evaluation, and application of interpretable machine learning models. Topics of interest include novel approaches, metrics and benchmarks, mechanistic interpretability methods, comparative studies, domain knowledge integration, and applications in diverse domains. Submissions should be anonymized and use the official template, and can be up to 6 pages long with unlimited references and supplementary materials. The workshop is non-archival and will not have formal proceedings. Important dates include submission open on August 9, 2024, notification of acceptance on October 9, 2024, and the workshop date on December 14 or 15, 2024. For inquiries, please contact interpretable.ai.neurips.workshop@gmail.com.