Research

Welcome! I am a PhD student at the German Research Center for Artificial Intelligence (DFKI) and Saarland University. I work in the E&E group (Efficient and Explainable NLP Models, led by Simon Ostermann) within DFKI's Multilinguality and Language Technology department, contributing to the TRAILS and SOOFI projects. I am interested in how large language models represent and use knowledge across languages and cultures, and in the tools that let us look inside them.

My current work centers on three threads:

  • Mechanistic interpretability for multilingual models. I train and analyze sparse autoencoders (SAEs) across languages and architectures, from Llama, Qwen, and Gemma to hybrid Mamba-attention models, to understand which features are shared across languages and which are language-specific.
  • Steering and controlled generation. Building on interpretability, I develop activation-steering methods that push multilingual models toward cultural knowledge, better low-resource synthetic data, and controlled linguistic behavior such as tense.
  • Culturally sensitive and inclusive NLP. I study how cultural and locale-specific knowledge is encoded in models, including contamination-robust translation benchmarks, stereotype tracing, and dialectal Arabic speech processing.

Earlier in my PhD I worked on document-level neural machine translation, exploring how web-crawled parallel data such as ParaCrawl can be used beyond the sentence level.

Multilingual NLP · interpretability · sparse autoencoders · activation steering · machine translation · cultural knowledge in LLMs

Publications

Also on Google Scholar.

2026

  1. Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection Yusser Al Ghussin, Daniil Gurgurov, Tanja Baeumel, Josef van Genabith, Patrick Schramowski, et al. 6th Workshop on Trustworthy NLP (TrustNLP 2026)
  2. DFKI-MLT at SemEval-2026 Task 7: Steering Multilingual Models towards Cultural Knowledge Yusser Al Ghussin, Daniil Gurgurov, Yasser Hamidullah, Josef van Genabith, et al. 20th International Workshop on Semantic Evaluation (SemEval 2026)
  3. CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark Daniil Gurgurov, Yusser Al Ghussin, Tanja Baeumel, Chen-Tse Chou, Patrick Schramowski, et al. arXiv:2601.08331
  4. Tracing Stereotypes from Representation to Output in Multilingual LLMs Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pin-Jie Chen, Josef van Genabith, Koel Dutta Chowdhury arXiv:2609.08322
  5. Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation Yasser Hamidullah, Koel Dutta Chowdhury, Yusser Al Ghussin, Sepehr Yazdani, Cennet Oguz, et al. International Conference on Learning Representations (ICLR 2026)
  6. Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin, Simon Ostermann arXiv:2606.18389
  7. Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness Pin-Jie Chen, Koel Dutta Chowdhury, Xintong Xu, Daria Tan, Deborah Osmelak, Ona de Gibert, et al. (incl. Yusser Al Ghussin) arXiv:2608.09766

2025

  1. TenseLoC: Tense Localization and Control in a Multilingual LLM Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, David Mareček, Josef van Genabith, et al. 5th Workshop on Multilingual Representation Learning (MRL 2025)
  2. Saarland-Groningen at NADI 2025 Shared Task: Effective Dialectal Arabic Speech Processing under Data Constraints Badr M. Abdullah, Yusser Al Ghussin, Zena Al-Khalili, et al. Third Arabic Natural Language Processing Conference (ArabicNLP 2025)
  3. Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation Daniil Gurgurov, Katharina Trinley, Yusser Al Ghussin, Tanja Baeumel, Josef van Genabith, et al. 14th International Joint Conference on Natural Language Processing (IJCNLP-AACL 2025)
  4. Modular Arithmetic: Language Models Solve Math Digit by Digit Tanja Baeumel, Daniil Gurgurov, Yusser Al Ghussin, Josef van Genabith, Simon Ostermann 14th International Joint Conference on Natural Language Processing (IJCNLP-AACL 2025)

2023

  1. Exploring Paracrawl for Document-level Neural Machine Translation Yusser Al Ghussin, Jingyi Zhang, Josef van Genabith 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023)

Software & Models

I release most of my research artifacts openly, with over 100 models and 20 datasets on Hugging Face, and code on GitHub. Highlights:

  • nemotron-lens TransformerLens-style interpretability tooling for NVIDIA Nemotron hybrid models (Mamba-2 + attention + MoE): hook any location, cache activations, train JumpReLU SAEs, and evaluate them with SAE-Bench (PyPI).
  • MULTI21-SAES Multilingual sparse autoencoder suites for Qwen3, Llama 3.1, and Gemma 2, from the work on multilingual steering by design.
  • FineWeb-CLaR Culture- and region-annotated corpora derived from FineWeb, for studying cultural and locale signals in pretraining data.
  • Cultural NLP Hub A living, filterable catalog of cultural-NLP datasets with multi-annotator coding and a community submission workflow (code).

Service

  • Member of the E&E group (Efficient and Explainable NLP Models) at DFKI's Multilinguality and Language Technology department.
  • Researcher on the TRAILS project (Trustworthy and Inclusive Machines), funded by the German Federal Ministry of Research, Technology and Space.
  • Researcher on the SOOFI project, building European foundation models on European infrastructure (IPCEI-CIS / 8ra). My work includes the Soofi-SAEs interpretability suite.
  • Shared-task participant and system builder: SemEval-2026 Task 7 (cultural knowledge) and NADI 2025 (dialectal Arabic speech processing).
  • Open-source contributor to the multilingual interpretability ecosystem, including SAE training pipelines, benchmarks, and datasets.