Ayer uno de nuestros investigadores, Oscar Sainz (@osainz.bsky.social), fue galardonado con el premio a la mejor tesis doctoral en Inteligencia Artificial por la Asociación Española para la Inteligencia Artificial (AEPIA). ¡Enhorabuena! 🥳
10.07.2025 07:25 — 👍 5 🔁 2 💬 0 📌 0
«Kaixo, Latxa naiz. Zer jakin nahi duzu gaur?»
Euskarazko txatbota sortu du EHUko HiTZ ikerketa zentroak. Oraindik ez dute jendaurrean zabaldu, baina garatzaileek eta enpresek eskuratzeko aukera dute. BERRIAko testuak erabili dituzte Latxa entr...
«Kaixo, Latxa naiz. Zer jakin nahi duzu gaur?». Euskarazko txatbota sortu du EHUko HiTZ ikerketa zentroak. Oraindik ez dute publikora zabaldu, baina garatzaileek eta enpresek eskuratzeko aukera dute. BERRIAko testuak erabili dituzte Latxa entrenatzeko.
t.co/OPVNnBG2xW?utm_...
16.06.2025 21:00 — 👍 2 🔁 3 💬 0 📌 1
While the experiments were not complicated, they required the collaboration of amazing co-authors, many compute hours, and of course, the impressive collaboration of the Basque community that was involved in manually assessing the models on an arena style evaluation.
Thank you!
11.06.2025 18:01 — 👍 1 🔁 1 💬 0 📌 0
In this work we face the challenge of developing instruct models for Basque, a low-resource language.
Continue pretraining base models is intuitive, but what about instructed models? We analyze systematically all different approaches to find the best solution.
2/3
11.06.2025 18:01 — 👍 2 🔁 1 💬 1 📌 0
Do you know that you can continue pretraining Instructed LLMs without losing their instruction following capabilities?
We did so to teach Basque to Llama models with promising results!
Interestingly, you only need English instructions and target language corpora 🤯
1/3
11.06.2025 18:01 — 👍 6 🔁 3 💬 1 📌 0
[1/7]
#newHitzPaper
Many languages are underserved by open LLMs, and face the following question: Which is the best way to produce open instruction-tuned LLMs for low-resource languages?
We obtained great results for a cost-effective option!
📄Paper: arxiv.org/abs/2506.07597
11.06.2025 10:27 — 👍 7 🔁 3 💬 1 📌 0
Dibujadora
Actualmente arruinándome la vida escribiendo Makomia
PhD Student @HelsinkiNLP / Low-resource, Machine Translation, Knowledge Distillation, Multilinguality
自然言語処理やってるはず...週8筋トレゴリラ。進捗は筋肉です！将来の夢はボディービルダー！ NAIST
PhD student at HiTZ Zentroa (@hitz-zentroa.bsky.social) / IXA Group and the University of Basque Country (@upvehu.bsky.social).
NLP PhD student at @naist-nlp.bsky.social
Permanent researcher at HiTZ Center - Ixa, University of the Basque Country UPV/EHU. https://ragerri.github.io/
#NLProc
#NLP
Assistant professor at UPV/EHU @hitz-zentroa.bsky.social. He/him. #NLP for low-resource settings, currently very interested in evaluation methodology. http://jerbarnes.github.io
Asst prof @ University of Utah · NLP · she/her 🇭🇷
Professor, Programmer in NYC.
Cornell, Hugging Face 🤗
Stanford Linguistics and Computer Science. Director, Stanford AI Lab. Founder of @stanfordnlp.bsky.social . #NLP https://nlp.stanford.edu/~manning/
Associate professor at IT University of Copenhagen: NLP, language models, interpretability, AI & society. Co-editor-in-chief of ACL Rolling Review. #NLProc #NLP
AI for storytelling, games, explainability, safety, ethics. Professor at Georgia Tech. Associate Director of ML Center at GT. Time travel expert. Geek. Dad. he/him
Professor, Santa Fe Institute. Research on AI, cognitive science, and complex systems.
Website: https://melaniemitchell.me
Substack: https://aiguide.substack.com/
I like tokens! Lead for OLMo data at @ai2.bsky.social (Dolma 🍇) w @kylelo.bsky.social. Open source is fun 🤖☕️🍕🏳️🌈 Opinions are sampled from my own stochastic parrot
more at https://soldaini.net
Book: https://thecon.ai
Web: https://faculty.washington.edu/ebender
Researcher trying to shape AI towards positive outcomes. ML & Ethics +birds. Generally trying to do the right thing. TIME 100 | TED speaker | Senate testimony provider | Navigating public life as a recluse.
Former: Google, Microsoft; Current: Hugging Face
Host of scientistic papers for @aclmeeting.bsky.social and other venues in the field of natural language processing. https://aclanthology.org/
#NLP #NLProc
