Shaoxiong is a principal investigator at ELLIS Institute Finland and an assistant professor at University of Turku, Finland. Prior to this, he was an independent research group leader at Technical University of Darmstadt, and a postdoctoral researcher at the University of Helsinki, working on high-performance language technology. He obtained his Ph.D. at Aalto University. [MORE]

Research Group

Our research group at the ELLIS Institute Finland & TurkuNLP, University of Turku focuses on advancing natural language processing and machine learning with applications in healthcare and multilingual scenarios. We work on cutting-edge topics including LLM post-training, multilingual NLP for low-resource languages, and AI for healthcare.

We are committed to:

    Developing robust ML and NLP systems for diverse tasks and domains

    Creating multilingual LLMs that serve underrepresented languages

    Advancing AI applications in healthcare with a focus on trustworthiness and fairness

    Training the next generation of researchers in AI and NLP

Meet our people →

We welcome Master's students who are looking for thesis opportunities and visiting students and researchers in NLP and related fields to work with us.


What's New

Thrilled to have Mingyuan Li join the team as a postdoc researcher – welcome aboard!

May 8, 2026 @Espoo, Finland

Two papers accepted by ACL Findings 2026: one on multilingual CPT (EMMA-500) and another on AI for mental health (PsyDefConv) EMMA-500 paper on arXiv PsyDefConv paper on arXiv

April 7, 2026

Thrilled to have Yicong Wu & Naveen Vakada join the team as doctoral researchers – welcome aboard!

March/April 2026 @Turku, Finland

Invited to serve as publication chairs for EMNLP 2026

February 2026

Our survey on LLM for graph learning is now available in the ACM Digital Library. ACM Digital Library entry for the survey

Feb 17, 2026

XMPIE, a parallel multilingual and multimodal dataset of potentially idiomatic expressions, landed at LREC 2026. Link to XMPIE preprint on arXiv

Feb 16, 2026

We are now seeking postdoctoral researchers to join the ELLIS Institute Finland. Postdoctoral recruit announcement Postdoc recruitment post

Jan 12, 2026

Thrilled to have Renhao Pei join the team as a doctoral researcher – welcome aboard!

Jan 12, 2026 @Turku, Finland

Call for participation in the PsyDefDetect Shared Task at BioNLP, ACL 2026 for detecting psychological defense mechanisms in conversations. PsyDefDetect shared task announcement

Start on March 15, 2026 @BioNLP, ACL 2026

A paper on reasoning models for MT was accepted by EACL 2026. EACL 2026 MT reasoning paper

January 4, 2026 @Rabat, Morocco

Thrilled to join ELLIS Institute Finland as a Principal Investigator hosted at the University of Turku. UTU news article about the appointment

October 1, 2025 @Finland

EMMA-500 Llama 3/3.1 models and the MaLA bilingual translation corpus now cover 2,500+ language pairs. EMMA-500 release

June 2025

GlotEval, a test suite for massively multilingual evaluation of LLMs, released its preview. GlotEval repository

April 2025

A series of CPT models explores data mixing in continual pre-training. Hugging Face CPT collection

April 2025




Locations

Click the button to lazy load campus maps for ELLIS Institute Finland and TurkuNLP, University of Turku.

Left: ELLIS Institute Finland (Maarintie 8, Espoo) · Right: TurkuNLP, University of Turku (Agora, Turku).