Understanding Annotator Safety Policy with Interpretability

Alex Oesterling, Donghao Ren, Yannick Assogba, Dominik Moritz, Sunnie S. Y. Kim, Leon A. Gatys, Fred Hohman. Understanding Annotator Safety Policy with Interpretability. In Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2026, Montreal, QC, Canada, June 25-28, 2026. pages 5653-5690, ACM, 2026. [doi]

@inproceedings{OesterlingRAMKG26,
  title = {Understanding Annotator Safety Policy with Interpretability},
  author = {Alex Oesterling and Donghao Ren and Yannick Assogba and Dominik Moritz and Sunnie S. Y. Kim and Leon A. Gatys and Fred Hohman},
  year = {2026},
  doi = {10.1145/3805689.3806472},
  url = {https://doi.org/10.1145/3805689.3806472},
  researchr = {https://researchr.org/publication/OesterlingRAMKG26},
  cites = {0},
  citedby = {0},
  pages = {5653-5690},
  booktitle = {Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2026, Montreal, QC, Canada, June 25-28, 2026},
  publisher = {ACM},
  isbn = {979-8-4007-2596-8},
}