Oral presentation at NAACL 2024: 'You don’t need a personality test to know these models are unreliable' (co-first author)
Paper accepted at NAACL 2025: 'Causally Modeling the Linguistic and Social Factors that Predict Email Response' (co-first author)
Oral presentation at ACL 2025: 'FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation'
Paper in ACL 2025 Findings: 'Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)'
Multiple preprints under review, including 'SPRIG', 'Latent Geographies', 'VeriFact', and 'Real or Robotic?', covering system prompting, factuality evaluation, and human-AI dialogue simulation