Teddy Ferdinan
PhD Student
Teddy Ferdinan is a PhD candidate in the Department of Artificial Intelligence at Wrocław University of Science and Technology. He graduated from the Bachelor's degree program in Informatics at Universitas Katolik Musi Charitas, Indonesia, in 2019. Afterwards, he received the NAWA Ignacy Łukasiewicz Scholarship in 2020. In 2023, he earned the Master's degree in Applied Computer Science from Wrocław University of Science and Technology, ranking second in the faculty-level TOP-10 competition for the best graduates of the year. He started his PhD in October 2023, during which he also received the NCN scholarship from project "Personalized Reasoning in Natural Language Processing".
Currently, his research focuses on large language models and natural language processing, specifically continual learning and transfer learning methods, as well as knowledge boundary probing. He has published works in renowned journals and conferences such as Information Fusion, IEEE Intelligent Systems, ACL, and EMNLP, some of which resulted from international collaboration. Most recently, he contributed to the CLARIN-PL research project, PLLuM and its continuation HIVE AI.
Publications14
What properties of reasoning supervision are associated with improved downstream model quality?
M Langner, D Pihulski, JK Eliasz, M Rajkowski, P Kazienko, M Piasecki, J Kocoń, T Ferdinan
ICCS 2026 276–292
Breaking the illusion of reasoning in Polish LLMs: quality over quantity of thought
D Pihulski, M Langner, J Eliasz, P Kazienko, J Kocoń, T Ferdinan, …
EACL 2026 1796–1811
Architectural concepts for integrating fundamental drives and emotions into artificial intelligence
T Ferdinan, WM Mieleszczenko-Kowszewicz, J Kocoń, P Kazienko
IEEE 2025
Java source code vulnerability detection using large language model
DR Anbiya, T Ferdinan, G Kołaczek
29th International Conference on Knowledge Based and Intelligent information and Engineering Systems (KES 2025) 2828–2837
AggTruth: contextual hallucination detection using aggregated attention scores in LLMs
PJ Matys, JK Eliasz, KM Kiełczyński, M Langner, T Ferdinan, J Kocoń, P Kazienko
ICCS 2025 227–243
Fortifying NLP models against poisoning attacks: The power of personalized prediction architectures
Information Fusion 114, 1–19 · Cited by 5
Into the unknown: Self-learning Large Language Models
T Ferdinan, J Kocoń, P Kazienko
24th IEEE International Conference on Data Mining Workshops, ICDMW 2024, 9 December 2024, Abu Dhabi, United Arab Emirates 423–432 · Cited by 6
Eagle and Finch: RWKV with matrix-valued states and dynamic recurrence
B Peng, D Goldstein, Q Anthony, A Albalak, E Alcaide, S Biderman, …, T Ferdinan, …, P Kazienko, …, J Kocoń, B Koptyra, …, S Woźniak, …
Conference paper · Cited by 10
Self-training large language models through knowledge detection
T Ferdinan, P Kazienko, WJ Yeo, R Satapathy, E Cambria
EMNLP 2024 15033–150451
Incidence of heart disease and stroke among patients with bipolar disorder
DM Krzyżanowski, T Ferdinan, R Szczepanowski, J Kulińska, M Palej-Cieplińska, GH Ibarburu
2024 23, 86–86
StudEmo: A Non-aggregated Review Dataset for Personalized Emotion Recognition
A Ngo, A Candri, T Ferdinan, J Kocoń, W Korczyński
LREC 2022 46–55