🔬 Works of MIT Lincoln Laboratory from 2026

4 works · the most cited first · ← MIT Lincoln Laboratory

1. DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English DialectsAnnual Meeting of the Association for Computational Linguistics (ACL)Jason S Lucas, Matt Murtagh White, Ali Al-Lawati, et al.2026
2. Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic DetectionAnnual Meeting of the Association for Computational Linguistics (ACL)Adaku Uchendu2026
3. The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent SpacesAnnual Meeting of the Association for Computational Linguistics (ACL)Angelina Tsai, Shreya Subramanian, Catherine Liu, et al.2026
4. Using Topological Data Analysis to Characterize the Layers of Language Models Before and After Word Substitution AttacksWorkshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or IndividualAdam Tang, Catherine Liu, Kimberly Lopez, et al.2026

This page in Markdown → https://md.research.elamur.ai/free/en/labs/mit-lincoln-laboratory/year/2026/