Faeze Ghorbanpour

Hi!

I’m Faeze, a PhD student at TU Munich, under supervision of Prof. Alexander Fraser. I am affiliated with the Munich Center for Machine Learning (MCML).

My research centers on making NLP systems more efficient, inclusive, and applicable to real-world problems. My current research focuses on efficient transfer learning for generalizable harmful content detection—a challenging and socially impactful task. I’m especially interested in topics such as efficient and compact language models, low-resource and multilingual NLP, and the intersection of language technology and social impact. These interests are tightly connected by a common goal: enabling robust, fair, and accessible NLP across diverse languages and domains.

If any of this resonates with you—or if you’re just curious about my work—feel free to reach out.
I’m always open to new collaborations and conversations! 🚀

news

Mar 01, 2026	🚀 Excited to be visiting Prof. Anders Søgaard’s NLP group at the University of Copenhagen 🇩🇰. Looking forward to the collaboration and the project we will be working on together. 🤝
Aug 20, 2025	🎉 Our work “Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data” has been accepted for publication at EMNLP 2025! 🎊
Jun 14, 2025	🎉 Our paper “Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study” has been accepted to WOAH at ACL 2025! 🥳
Mar 15, 2025	🎉 Our paper “Differentiating Emigration and Return Migration” has been accepted at ICWSM 2025! ✨ This work is from my research visit at MPIDR, Rostock, Germany.
Dec 15, 2024	🎉 Our paper “Label-Specific Representation and Knowledge Transfer for Harmful Content Detection” has been accepted at NAACL 2025! ✨

selected publications

Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data

Faeze Ghorbanpour, Daryna Dementieva, and Alexander Fraser

In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

DOI Bib

@inproceedings{ghorbanpour-etal-2025-data,
  title = {Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data},
  author = {Ghorbanpour, Faeze and Dementieva, Daryna and Fraser, Alexander},
  editor = {Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  address = {Suzhou, China},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.emnlp-main.1507/},
  doi = {10.18653/v1/2025.emnlp-main.1507},
  pages = {29674--29692},
  isbn = {979-8-89176-332-6},
}

Fine-Grained Transfer Learning for Harmful Content Detection through Label-Specific Soft Prompt Tuning

Faeze Ghorbanpour, Viktor Hangya, and Alexander Fraser

In NAACL (Main), 2025

DOI Bib

@inproceedings{Ghorbanpour2025Fine,
  title = {Fine-Grained Transfer Learning for Harmful Content Detection through Label-Specific Soft Prompt Tuning},
  author = {Ghorbanpour, Faeze and Hangya, Viktor and Fraser, Alexander},
  booktitle = {NAACL (Main)},
  year = {2025},
  doi = {https://doi.org/10.18653/v1/2025.naacl-long.551},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.naacl-long.551/},
}

FNR: A Similarity and Transformer-Based Approach to Detect Multi-Modal Fake News in Social Media

Faeze Ghorbanpour, Maryam Ramezani, Mohammad Amin Fazli, and 1 more author

Social Network Analysis and Mining, 2023

DOI Bib

@article{ghorbanpour2023fnr,
  title = {FNR: A Similarity and Transformer-Based Approach to Detect Multi-Modal Fake News in Social Media},
  author = {Ghorbanpour, Faeze and Ramezani, Maryam and Fazli, Mohammad Amin and Rabiee, Hamid R},
  journal = {Social Network Analysis and Mining},
  volume = {13},
  number = {1},
  pages = {56},
  year = {2023},
  publisher = {Springer},
  doi = {https://doi.org/10.1007/s13278-023-01065-0},
  url = {https://link.springer.com/article/10.1007/s13278-023-01065-0},
}