<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 initiated and organized PANDORA, a workshop @ EMNLP 2026 focused on pluralistic alignment and sociotechnical AI evaluation. I am also part of the organizing committee of the Natural Legal Language Processing (NLLP) workshop.

News

07/2025: Honoured to be part of the organizing committee of the NLLP workshop.
06/2025: I presented our paper at ICAIL 2026 in Singapore 🇸🇬.
05/2025: First time Area Chair at ACL ARR May 2026.
03/2026: Our workshop PANDORA is accepted to EMNLP2026. Stay tuned!
12/2025: I successfully defended my PhD defence! 🥳
11/2025: I presented our paper at NLLP@EMNLP 2025 in Suzhou 🇨🇳.
09/2025: Invited seminar at ⚖️ iCourts Research Center, Faulty of Law, University of Copenhagen.

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. Findinds ACL 2026.
**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)