Publications

1. 2026ACL Findings
   Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization
2. 2026CALD-pseudo @ LREC
   Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models
3. 2026EACL
   CALE: Concept-Aligned Embeddings for Both Within-Lemma and Inter-Lemma Sense Differentiation
4. 2026Nature
   A benchmark of expert-level academic questions to assess AI capabilities
5. 2025EMNLP
   Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization
6. 2025PrivateNLP @ NAACL
   TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods
7. 2024CODASPY
   WikiPhish: A Diverse Wikipedia-Based Dataset for Phishing Website Detection: Data/Toolset Paper
8. 2021NLP4MusA
   What Musical Knowledge Does Self-Attention Learn?