Research Overview

My research sits at the intersection of natural language processing, information integrity, and AI safety, with a focus on the systems and populations that current AI tooling has historically left behind. I build models, datasets, and evaluation frameworks that:

  • extend state-of-the-art NLP capabilities into low-resource and dialectal varieties of language,
  • probe the robustness and fairness of harmful content detectors under realistic adversarial pressure,
  • and develop equitable, transparent, and safe AI pipelines for combating mis/disinformation across linguistic communities.

Below is a high-level summary of my research themes. Detailed papers, datasets, and code are linked from each.

Research Themes

1. Multilingual & Low-Resource NLP

Extending modern NLP techniques — fine-tuning, prompt-based learning, retrieval, and adversarial training — beyond English into the long tail of low-resource languages and dialects. My BLUFF benchmark spans 79 languages (20 high-resource + 59 low-resource) with 200K+ samples, and DIA-HARM evaluates robustness across 50 English dialects.

  • BLUFF — multilingual fake news detection benchmark
  • DIA-HARM — dialectal robustness for harmful content detection (ACL 2026)

2. Harmful Content Detection & Information Integrity

Building robust, equitable detection systems for mis/disinformation, harmful content, and AI-generated text — and rigorously characterizing where and why they fail. My work consistently shows that detector performance gaps along language, dialect, and resource axes are systematic, not marginal.

  • F3 — LLMs as both generators and detectors of elusive disinformation (EMNLP 2023)
  • MULTITuDe — multilingual machine-generated text detection (EMNLP 2023)
  • X-Transfer — cross-lingual transfer for misinformation detection

3. Adversarial ML & AI Safety

Understanding the threat surface of modern language systems — jailbreaking, hallucination, dialectal evasion, agentic adversaries — and designing defenses that hold up under realistic, non-Standard-American-English inputs.

4. Equity & Accessibility in AI

Drawing on my Grenadian background and knowledge of Caribbean Creole varieties, I bring a global perspective to AI fairness, focused on ensuring that the next generation of AI systems serves the linguistic communities most often left out of training data.

Research Statements

Detailed statements describing my research vision, teaching philosophy, and commitment to diversity, equity, and inclusion are available below.

  • Research Statementcoming soon
  • Teaching Statementcoming soon
  • Diversity, Equity & Inclusion Statementcoming soon

For the most up-to-date overview, please see my CV or contact me directly.