⚠️ Preprint alert ⚠️ ⭐ Excited to share our new paper on mitigating cross-lingual cultural inconsistency in LLMs! We explore why multilingual models vary their answers based purely on the prompt language, even when a user persona is explicitly fixed. 🧵👇

📢⚠️ IMPORTANT DATE CORRECTION: the ARR deadline for EACL 2027 is Aug 3, 2026 (not Aug 6 as previously announced). EACL is earlier than usual in '27, so this is the only viable ARR cycle! 📚 All areas of CL/NLP + related fields welcome. Full CfP coming soon. #NLProc #EACL2027

Thrilled to announce that my survey paper has been accepted at #EMNLP2025 Main! 🎉 To our knowledge, this is the first comprehensive survey dedicated to multilingual explainability. 📄 Preprint: openreview.net/forum?id=KQj... w/ Anna Korhonen, @iaugenstein.bsky.social #NLP #ExplainableAI