Miriam Wanner

PhD Student, Johns Hopkins University

About Me

I am currently a 4th year PhD student at the Center for Language and Speech Processing (CLSP) at Johns Hopkins University, co-advised by Mark Dredze and Will Walden. Previously, I received my bachelor’s degree in computer science and math (double major) from the University of Virginia, where I spent some time researching kelp ecology. My research interests are in natural language processing, particularly in model personas and emergent misalignment.

Miriam Wanner

Publications

    2026

  1. Miriam Wanner, Mark Dredze, William Walden. On the Threat Model of Weird Generalization and Emergent Misalignment. 2026. [preprint]
  2. Miriam Wanner, Hannah Collison, William Jurayj, Benjamin Van Durme, Mark Dredze, William Walden. Weird Generalization is Weirdly Brittle. 2026. [preprint]
  3. William Walden and Miriam Wanner. Reasoning Models Will Sometimes Lie About Their Reasoning. 2026. [preprint]
  4. Sathvik Napa, Utkarsh Singh, Chengyuan Xue, Miriam Wanner, William Walden. Can Reasoning Models Detect Changes to their Chains of Thought?. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026. [preprint]
  5. Miriam Wanner, Leif Azzopardi, Paul Thomas, Soham Dan, Benjamin Van Durme, Nick Craswell. All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM Generations. In Findings of Empirical Methods in Natural Language Processing (EMNLP), 2026. [preprint]
  6. William Walden, Kathryn Ricci, Miriam Wanner, Zhengping Jiang, Chandler May, Rongkun Zhou, Benjamin Van Durme. How Grounded is Wikipedia? A Study on Structured Evidential Support. In Findings of the Association for Computational Linguistics (ACL), 2026. [preprint]
  7. Miriam Wanner, Sophia Hager, Anjalie Field. Does Local News Stay Local?: Online Content Shifts in Sinclair-Acquired Stations. Proceedings of the Seventh Workshop on Natural Language Processing and Computational Social Science (NLP+CSS), 2026. [preprint]

    8. 2025

  8. Miriam Wanner, Benjamin Van Durme, Mark Dredze. DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. [paper]
  9. Jiefu Ou, William Gantt Walden, Kate Sanders, Zhengping Jiang, Kaiser Sun, Jeffrey Cheng, William Jurayj, Miriam Wanner, Shaobo Liang, Candice Morgan, Seunghoon Han, Weiqi Wang, Chandler May, Hannah Recknor, Daniel Khashabi, Benjamin Van Durme. CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers? In Findings of Empirical Methods in Natural Language Processing (EMNLP). 2025. [paper]
  10. Zhengping Jiang, Jingyu Zhang, Nathaniel Weir, Seth Ebner, Miriam Wanner, Kate Sanders, Daniel Khashabi, Anqi Liu, Benjamin Van Durme. Core: Robust Factual Precision Scoring with Informative Sub-Claim Identification. In Findings of the Association for Computational Linguistics (ACL), 2025. [paper]

    11. 2024

  11. Miriam Wanner, Seth Ebner, Zhengping Jiang, Mark Dredze, Benjamin Van Durme. A Closer Look at Claim Decomposition. *SEM, 2024. [paper]
  12. Miriam S. Wanner, Jonathan A. Walter, Daniel C. Reuman, Tom W. Bell, & Max C.N. Castorani. Dispersal synchronizes giant kelp forests. Ecology, 2024. [paper]

    13. 2022

  13. Nathaniel Krasner, Miriam Wanner, Antonios Anastasopoulos. Revisiting the Effects of Leakage on Dependency Parsing. In Findings of the Association for Computational Linguistics (ACL), 2022. [paper]

CV

My CV can be found here.