Antonia Karamolegkou, Oliver Eberle, Phillip Rust, Carina Kauf, Anders S{\o}gaard
Trick or Neat: Adversarial Ambiguity and Language Model Evaluation
https://arxiv.org/abs/2506.01205

Also huge thanks to @iamdddaryna.bsky.social and @zhijingjin.bsky.social, your support has been really invaluable! 💝

This work stems from conversations at the @nlp4posimpact.bsky.social Workshop at #EMNLP2024 @emnlpmeeting.bsky.social.

Huge thanks to all collaborators, attendees, and supporters who shaped this effort. 🎉

📄 Preprint: arxiv.org/pdf/2505.22327

🌍 How can #NLP & #LLMs help tackle global challenges?

💡 We map 9 key domains to the UN SDGs & the Global Risks Report 2025, highlighting open challenges, overlooked opportunities, and paths toward responsible deployment.

#NLP4SG #AI4SG #ResponsibleAI #NLP4PI