Byron C. Wallace
Professor, Khoury College of Computer Sciences, Northeastern University
Research Interests
I work on natural language processing and machine learning, with applications in healthcare and other high-stakes domains. I am especially interested in model interpretability, analysis, and evaluation.
Recent Papers
- Do Natural Language Interpretability Methods Convey Privileged Information? Proceedings of the International Conference on Machine Learning (ICML), 2026.
- Interpretability Can Be Actionable Proceedings of the International Conference on Machine Learning (ICML), 2026.
- Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence Proceedings of the Findings of Conference of the Association for Computational Linguistics (ACL), 2026.
- Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine Proceedings of the Findings of Conference of the Association for Computational Linguistics (ACL), 2026.
- Can SAEs reveal and mitigate racial biases of LLMs in healthcare? Proceedings of the International Conference on Learning Representations (ICLR), 2026.
- Large language models require a new form of oversight: capability-based monitoring npj Digital Medicine, 2026.