Welcome!

I am a Statistics + CSE PhD student at the University of Washington researching AI alignment, safety, and impact.

Advised by Yejin Choi in the Paul G. Allen School of Computer Science and Engineering and Thomas Richardson in the Statistics Department, my focus in on projects that leverage statistical tools to advance methods and insights in human-centric NLP challenges. Currently, my work centers on alignment, controllable generations, and impact of AI on society.


Jillian Fisher

Preprints

  1. Fisher, J., Feng, S., Aron, R., Richardson, T., Choi Y., Fisher, D., Pan J., Tsvetkov, Y., & Reinecke, K (2024) . Biased AI can Influence Political Decision-Making. arxiv.org/abs/2410.06415.

Conference Proceedings

  1. Fisher, J., Hallinan, S., Lu, X., Gordon, M., Harchaoui, Z., & Choi, Y. StyleRemix: Interpertable Authorship Obfuscation via Distillation and Perturbation of Style Elements. EMNLP (2024). http://www.arxiv.org/abs/2408.15666
  2. Feng, S., Sorensen, Taylor., Liu, Y., Fisher, J., Young Park, C., Choi, Y., & Tsvetkov, Y. Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration. EMNLP (2024). https://arxiv.org/abs/2406.15951.
  3. Sorensen, T., Moore, Jared., Fisher, J., Gordon, M., Mireshghallah, N., Rytting, C., Ye, A., Jiang, L., Lu, X., Dziri, N., Althoff, T., & Choi, Y. A Roadmap to Pluralistic Alignment. ICML (2024). https://arxiv.org/abs/2402.05070
  4. Fisher, J., Lu, X., Jung, J., Jiang, L., & Choi, Y. JAMDEC: Unsupervised Authorship Obfuscation using Contrained Decoding over Small Language Models. NAACL (2024). https://arxiv.org/abs/2402.08761.
  5. Jung, J., West, P., Jiang, L., Brahman, F., Lu, X., Fisher, J., Sorensen, T., & Choi, Y. Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing. NAACL (2023). https://arxiv.org/abs/2305.16635.
  6. West, P., Lu, X., Dziri, N., Brahman, F., Li, L., Hwang, J. D., Jiang, L., Fisher, J., Ravichander, A., Chandu, K., Newman, B., Koh, P. W., Ettinger, A., & Choi, Y. The Generative AI Paradox: "What It Can Create, It May Not Understand". ICLR (2024). https://arxiv.org/abs/2311.000595.
  7. Lu, X., Brahman, F., West, P., Jung, J., Chandu, K., Ravichander, A., Ammanabrolu, P., Jiang, L., Ramnath, S., Dziri, N., Fisher, J., Lin, B., Hallinan, S., Qin, L., Ren, X., Welleck, S., & Choi, Y. Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning. EMNLP (2023). https://aclanthology.org/2023.emnlp-main.424.
  8. Fisher, J., Liu, L., Pillutla, K., Choi, Y., & Harchaoui, Z. Statistical and Computational Guarantees for Influence Diagnostics. AISTAT (2023). https://proceedings.mlr.press/v206/fisher23a/fisher23a.pdf.

Journal Articles

  1. O.Baird, S., Rinck, M., Rosenfield, D., Davis, M. L., Fisher, J., Becker, E. S., Powers, M. B., & Smits, J. A. J. Reducing approach bias to achieve smoking cessation: A pilot randomized placebo-controlled trial. Cognitive Therapy and Research (2017), 4(41).
Dictionary: