Verena Blaschke

Non-English NLP papers face a surprisingly high bias tax in peer review, often stemming from reviewers demanding unjustified cross-lingual generalization.

LLMs often fail to access knowledge uniquely available in lower-resource language varieties, even when closely related to high-resource languages, revealing a significant information asymmetry.

Even state-of-the-art multilingual transformers struggle with the pragmatic challenge of Indirect Question Answering, achieving low performance across English, German, and Bavarian.

Despite growing interest, queer NLP research remains largely reactive, highlighting biases instead of building proactive solutions, leaving significant opportunities for stakeholder-driven and intersectional approaches.