research CoBia Constructed conversations that trigger otherwise concealed societal biases in LLMs (EMNLP 2025, Oral). MEXA Multilingual evaluation of English-centric LLMs via cross-lingual alignment (ACL Findings 2025). GIRT Data and models for the automated generation of GitHub Issue Report Templates (MSR 2023 & 2024). Who Flips? Self- and cross-model counterarguments reveal answer instability in LLMs (Findings of EMNLP 2026). MenuCraft Interactive menu system design with large language models.