Irune Zubiaga

📢 We’re excited to announce that 16 𝗽𝗮𝗽𝗲𝗿𝘀 and 1 tutorial from the Hitz Center-Basque Center por Language Technology have been accepted at the #LREC2026 Conference. Proud to see HiTZ’s contributions to advancing the field of NLP! 🔝 lrec2026.info

HiTZ at #ACL2025NLP in Vienna!

Ostegunero, HiTZ zentroko kideak biltzen gara gure ikerketen berri emateko HiTZ mintegian. Aste honetan, bi tesi proiektu aurkeztu dira: @iruzubiaga-k "Learning to Judge: Automated Multilingual Evaluation of LLM-Generated Text" eta @Blanca_C_Fi "Critical Questions Generation"

🔬 Hitz zentroa Ikergazte 2025 kongresuan dago! Gure taldeko ikertzaileak bertan izan dira, euren ikerlanak aurkezten eta beste ikertzaile gazteekin harremanak sendotzen. 📊Taldeko 16 ikertzaile joan dira eta 12 lan aurkeztu dituzte.

We are in #coling2025!

The program for the Multilingual Counterspeech Generation Workshop is now live! 🎉 Excited to be part of the organizing team at @Hitz_zentroa, alongside @LanD_FBK and @NLP_SINAI. Looking forward to discussing this exciting topic in #COLING2025 in Abu Dhabi!

And here @iruzubiaga presenting the poster

We are in #EMNLP2024! @anaryegen, @Blanca_C_Fi and @iruzubiaga are presenting their works on argument mining, critical questions and counter-narrative evaluation

- Train and Development in Basque, English, Italian and English already available! - Participation in any language allowed. - Automatic evaluation scripts: github.com/hitz-zentroa/e… - Important dates: rb.gy/7alj7y - Organizers: @NLP_SINAI @LanD_FBK @Hitz_zentroa

Join us in the First Shared Task on the Multilingual Counterspeech Generation against Hate Speech! To be held @coling2025 Info: rb.gy/jfm481 - Aim: given a HS (and any additional knowledge the participants may like to use), generate a CN to counteract the HS.

Looking forward to discussing it further in Miami! 🙌

Our approach addresses a key issue: traditional metrics don’t correlate well with human judgment in Counter-Narrative evaluation. Using pairwise comparisons in a tournament-style format, we achieved a ρ score of 0.88! 📊 You can check out our paper here: arxiv.org/abs/2406.15227

🚨Happy to share that our paper “A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation" has been accepted at #EMNLP2024 Findings! 🎉 Congrats to all coauthors! @Aitor57 @ragerri @Hitz_zentroa @IxaTaldea