Faeze Ghorbanpour

Hi there! 👋

I’m a PhD student at TUM Munich, where I’m fortunate to be supervised by Prof. Alexander Fraser. I also work as an NLP researcher at CIS, LMU Munich and 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

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! ✨
Oct 27, 2024	I have moved to the TUM campus in Heilbronn, and after a year and two months as a PhD student at LMU Munich, I am now a PhD student at TU Munich.
Oct 05, 2024	I will be presenting the poster for “Label-Specific Soft Prompt Tuning” at the 2024 All-Hands Meeting of the National AI Centers in Dresden, Germany.
Aug 15, 2024	Our research paper on analyzing communication acts during crises will be presented at ASONAM 2024! This work is from my internship at Aalto University, Finaland.

selected publications

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

Faeze Ghorbanpour, Viktor Hangya, and Alexander Fraser

In NAACL, 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},
  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/},
}

Differentiating Emigration from Return Migration of Scholars Using Name-Based Nationality Detection Models

Faeze Ghorbanpour, Thiago Z. Malaguth, and Aliakbar Akbaritabar

In ICWSM, 2025

DOI Bib

@inproceedings{Ghorbanpour2025Differentiating,
  title = {Differentiating Emigration from Return Migration of Scholars Using Name-Based Nationality Detection Models},
  author = {Ghorbanpour, Faeze and Malaguth, Thiago Z. and Akbaritabar, Aliakbar},
  booktitle = {ICWSM},
  year = {2025},
  publisher = {AAAI},
  doi = {https://doi.org/10.1609/icwsm.v19i1.35836},
  url = {https://ojs.aaai.org/index.php/ICWSM/article/view/35836},
}

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},
}