DIA-HARM Wins Social Impact Paper Award at ACL 2026 🏆
Honored and humbled to share that our paper DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects received the 🏆 Social Impact Paper Award at the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) in San Diego, July 2–7, 2026.
The award recognizes work that meaningfully advances the field’s positive impact on society — a mission that sits at the heart of DIA-HARM. Current harmful-content detectors are built and evaluated almost exclusively on Standard American English, systematically disadvantaging hundreds of millions of non-SAE speakers worldwide. By benchmarking 16 models across 50 English dialects (U.S., British, African, Caribbean, and Asia-Pacific varieties) using the D3 corpus of 195K samples, we surfaced concrete equity gaps in content moderation — and gave the community a shared instrument to close them.
Deepest thanks to my incredible coauthors — Matt Murtagh-White, Ali Al-Lawati, Uchendu Uchendu, Adaku Uchendu, and my advisor Dr. Dongwon Lee — and to our collaborators at Penn State, MIT Lincoln Laboratory, and University College Dublin. And thank you to the ACL 2026 award committee for recognizing this line of work.
This award belongs equally to the linguistic communities whose voices are too often overlooked by AI systems. There is much more to do.
Resources:
I completed my Ph.D. in Informatics at Penn State University (defended May 2026; formal conferral August 2026), where I conducted research at the PIKE Research Lab under Dr. Dongwon Lee and the College of IST. Starting August 2026, I will join the Department of Information Science at the College of Media, Communication and Information (CMDI), University of Colorado Boulder, as a Tenure-Track Assistant Professor and founding Director of the Secure and Ethical AI Lab (SEAL). My research advances trustworthy and equitable AI for the world’s languages and communities — spanning multilingual NLP, low-resource and dialectal language technology, AI safety, and information integrity, with work extending across 70+ languages. I have authored 14+ peer-reviewed papers with 315+ citations in premier venues including ACL, EMNLP, NAACL, ICML, KDD, and IEEE.
My doctoral research focuses on bridging the digital language divide through transfer learning, classification (NLU), generation (NLG), adversarial attacks, and developing end-to-end AI pipelines using RAG and Agentic AI workflows for combating multilingual threats. Drawing from my Grenadian background and knowledge of local Creole languages, I bring a global perspective to AI challenges, working to democratize state-of-the-art AI capabilities for underserved linguistic communities worldwide. My mission is to develop robust multilingual multimodal systems and mitigate evolving security vulnerabilities while enhancing access to human language technology through cutting-edge solutions.
As an NSF LinDiv Fellow, I conduct transdisciplinary research advancing human-AI language interaction for social good. I actively mentor 5+ research interns and teach Applied Generative AI courses. Through industry experience at Lawrence Livermore National Lab, Interaction LLC, and Coalfire, I bridge academic research with practical applications in combating evolving security threats and enhancing global AI accessibility. I see multilingual advances and interdisciplinary collaboration as a competitive advantage, not a communication challenge. Beyond research, I stay active through dance, fitness, martial arts, and community service.