The Team

Team Co-lead

Suny Shtedritski

Team Co-lead

Hannah Kirk

Team Co-lead

Siobhan M Hall

Project Supervisor

Tim Franzmeyer

Project Supervisor

Laurynas Karazija

AI Labs

OxAI Labs is a student-led research organisation, focused on ML fairness. We do impactful research, while helping students develop AI research skills.

Join our labs team to collaborate on hands on AI projects. We organise projects for all levels, from novice to pro, and welcome people from all academic backgrounds..

Applications for this academic year:

Please fill in this form. The deadline for applications is 30th October. Students from all academic backgrounds are encouraged to apply

Labs Academic Publications:

  • VISOGENDER: A dataset for benchmarking gender bias in image-text pronoun resolution

    S. M. Hall, F. G. Abrantes, H. Zhu, G. Sodunke, A. Shtedritski and H. R. Kirk. (2023) NeurIPS Datasets and Benchmarks 2023

    Read the paper

  • Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models.

    Kirk, H. R., Jun, Y., Volpin, F., Iqbal, H., Benussi, E., Dreyer, F., Shtedritski, A., & Asano, Y. (2021). Advances in Neural Information Processing Systems, 34, 2611–2624.

    Read the paper

  • Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets

    B. Smith, M. Farinha, S. M. Hall, H. R. Kirk, A.Shtedritski, M. Bain (2023) NeurIPS workshop SyntheticData4ML

    Read the paper

  • A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning.

    Berg, H., Hall, S. M., Bhalgat, Y., Yang, W., Kirk, H. R., Shtedritski, A., & Bain, M. (2022). Proceedings of AACL - IJCNLP

    Read the paper

  • Memes in the wild: Assessing the generalizability of the hateful memes challenge dataset.

    Kirk, H., Jun, Y., Rauba, P., Wachtel, G., Li, R., Bai, X., Broestl, N., Doff-Sotta, M., Shtedritski, A., & Asano, Y. M. (2021). Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), 26–35.

    Read the paper

  • Privacy-Preserving Object Detection. Synthetic Data Generation Workshop (ICLR)

    He, P., Griffin, C., Kacprzyk, K., Joosen, A., Collyer, M., Shtedritski, A., & Asano, Y. M. (2021). ICLR Workshop on Syntetic Data Generation

    Read the paper

  • Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements.

    Borchers, C., Gala, D., Gilburt, B., Oravkin, E., Bounsi, W., Asano, Y. M., & Kirk, H. (2022). Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing.

    Read the paper