<aside>

</aside>

📩 Email

🦋Bsky

🎓 Google Scholar

I’m a Postdoctoral Researcher in NLP at the CoAStaL Lab at the University of Copenhagen. I completed my PhD in LegalNLP at TU Munich, supervised by Matthias Grabmair, and mentored by Barbara Plank. My research interest is Human-Centered AI , Legal NLP and AI Alignment to Pluralistic Human Values.

I am also an organizer of Munich🥨NLP, where I have organised get-together event to support and encourage women in NLP, and am committed to promoting diversity and inclusivity in the field.

News

09/2025: Invited seminar at ⚖️ iCourts Research Center, Faulty of Law, University of Copenhagen.
09/2025: Invited talk at DIKU Bits
09/2025: Joined CoAStaL Lab at University of Copenhagen as a Post Doc 🧜🏼‍♀️ !
08/2025: I presented our paper at L2M2@ACL 2025 in Vienna 🇦🇹.
06/2025: Invited talk at CoAStAL NLP @ University of Copenhagen 🇩🇰
08/2024: I presented our paper at ACL 2024 in 🇹🇭 Bangkok.
07/2024: Invited talk ****human label variations and alignment in legal NLP at Machine Learning Scientists in Legal Tech Social Session at ICML2024 🇦🇹

Selected Publications

From 🔇 Noise to 📶 Signal to 🎯 Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP. Shanshan Xu, T.Y.S.S Santosh, Barbara Plank. Under Review.
**Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court Cases.** Shanshan Xu, T.Y.S.S Santosh, Yanai Elazar, Quirin Vogel, Barbara Plank, Matthias Grabmair. L2M2@ACL 2025**.**
Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification. Shanshan Xu**,** Santosh T.Y.S.S, Oana Ichim, Barbara Plank, Matthias Grabmair. ACL 2024 (Oral).
From Dissonance to Insights: Dissecting Disagreements in Rationale Dataset Construction for Case Outcome Classification. *Shanshan Xu, **** *Santosh T.Y.S.S, Oana Ichim, Isabella Risini, Barbara Plank, Matthias Grabmair. EMNLP 2023.
**VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights.** Shanshan Xu, Leon Staufer, Santosh T.Y.S.S, Oana Ichim, Corina Heri, Matthias Grabmair. EMNLP 2023.
Deconfounding Legal Judgment Prediction towards Better Alignment with Experts for the European Court of Human Rights. Santosh T.Y.S.S, Shanshan Xu,** Oana Ichim, Matthias Grabmair. EMNLP 2022 (Oral; *Equal Contribution)