LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish
Fred Philippy, Siwen Guo, Jacques Klein, Tegawendé F. Bissyandé 2025. arXiv:2510.07074. Manuscript under review.
About Me
Hi, I'm Fred. I am a PhD candidate at the Interdisciplinary Centre for Security, Reliability and Trust (SnT) at the University of Luxembourg focusing on Natural Language Processing (NLP). My research is focused on multilingual language models and cross-lingual NLP, with a focus on low-resource languages and parameter-efficient methods.
Publications
Enhancing Small Language Models for Cross-Lingual Generalized Zero-Shot Classification with Soft Prompt Tuning
Fred Philippy, Laura Bernardy, Siwen Guo, Cedric Lothritz, Jacques Klein, Tegawendé F. Bissyandé 2025. In Proceedings of the 1st Workshop on Language Models for Underserved Communities, Albuquerque, NM, USA. Association for Computational Linguistics.
LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings
Fred Philippy, Siwen Guo, Jacques Klein, Tegawendé F. Bissyandé 2024. In Proceedings of the 31st International Conference on Computational Linguistics, pages 11369–11379, Abu Dhabi, UAE. Association for Computational Linguistics.
Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish
Fred Philippy, Shohreh Haddadan, Siwen Guo 2024. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024, pages 97-104, Torino, Italia. ELRA and ICCL.
Soft Prompt Tuning for Cross-Lingual Transfer: When Less is More
Fred Philippy, Siwen Guo, Shohreh Haddadan, Cedric Lothritz, Jacques Klein, Tegawendé F. Bissyandé. 2024. In Proceedings of the 1st Workshop on Modular and Open Multilingual NLP (MOOMIN 2024), pages 7–15, St. Julians, Malta. Association for Computational Linguistics.
Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A Review
Fred Philippy, Siwen Guo, and Shohreh Haddadan. 2023. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5877–5891, Toronto, Canada. Association for Computational Linguistics.
Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space
Fred Philippy, Siwen Guo, and Shohreh Haddadan. 2023. In Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, pages 22–29, Dubrovnik, Croatia. Association for Computational Linguistics.
Presentations & Conferences
- Department of Computer Science and Computer Engineering (DP-CSCE) Research Day 2025
Cross-Lingual Transfer in Multilingual LLMs (Invited as the previous year's poster award recipient)
October 2025 University of Luxembourg, Luxembourg - SnT Partnership Day
Natural Language Processing for Low-Resource Languages
May 2025 European Convention Center Luxembourg (ECCL), Luxembourg - 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)
Enhancing Small Language Models for Cross-Lingual Generalized Zero-Shot Classification with Soft Prompt Tuning
May 2025 Albuqerque, NM, USA - UniDive3rd General Meeting
Cross-Lingual Transfer In Multilingual Language Models: Impact of Linguistic Similarity And Parameter-Efficient Fine-Tuning
January 2025 Budapest, Hungary - The 31st International Conference on Computational Linguistics (COLING 2025)
LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings
January 2025 Abu Dhabi, United Arab Emirates - 4th International Conference 'Language in the Human-Machine Era'
Beyond Words: A Numerical Approach to Prompting Language Models
September 2024 UCLouvain, Louvain-la-Neuve, Belgium - European Language Data Space (LDS) Country Workshop
NLP for Low-Resource Languages
19th June 2024 Luxembourg Institute of Science and Technology, Luxembourg - Elements of AI: Closing Conference
NLP for Low-Resource Languages
7th June 2024 Digital Learning Hub, Luxembourg Digital Learning Hub, Luxembourg - 3rd Annual Meeting of the ELRA/ISCA SIG on Under-resourced Languages (SIGUL 2024), co-located with LREC-COLING 2024
Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish
May 2024 Turin, Italy
- 1st Workshop on Modular and Open Multilingual NLP (MOOMIN 2024), co-located with EACL 2024
Soft Prompt Tuning for Cross-Lingual Transfer: When Less is More
March 2024 St. Julians, Malta
- Foyer Hackathon 2023
Intelligence Artificielle Générative
7th November 2023 Leudelange, Luxembourg - Graduate NLP Course at OntarioTechU / University of Toronto
Cross-Lingual Transfer
2nd October 2023 Online - The 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)
Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A Review (Poster Presentation)
July 2023 Toronto, Canada
- 3rd International Conference 'Language in the Human-Machine Era'
Cross-Lingual Transfer Learning for Low-Resource Languages
May 2023 University of Groningen — Campus Fryslân, Leeuwarden, Netherlands - 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP 2023), co-located with EACL 2023
Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space
May 2023 Dubrovnik, Croatia
- 2nd International Conference 'Language in the Human-Machine Era'
30th June – 1st July 2022 University of Jyväskylä, Finland
Other Publications
Natural Language Processing als Stethoskop für das Erleben von Mitarbeitenden in der Industrie 5.0 (2022)
Marcus Heidbrink, Fred Philippy
In New Work in der Industrie (1st ed., pp. 226-230). Rossberg.
KI-Unterstützung bei der digitalen Personalauswahl – Eine Fallstudie im Unternehmer-Kontext (2023)
Hannah Kiesow-Berger, Michael Fell, Fred Philippy, Elias Steiner
In Personalauswahl 4.0: KI, Machine Learning, Gamification und andere Innovationen in der Praxis (pp. 163-177). Wiesbaden: Springer Fachmedien Wiesbaden.
Diagnostic tests for human Schistosoma mansoni and Schistosoma haematobium infection: a systematic review and meta-analysis (2024)
Michel T Vaillant, Fred Philippy, Jessica Barré, Dmitry Bulaev, Amadou T Garba
The Lancet Microbe
Characteristics and outcomes of COVID-19 patients admitted to hospital with and without respiratory symptoms (2024)
Barbara Wanjiru Citarella, Christiana Kartsonaki, Elsa D Ibáñez-Prada, . . . , Fred Philippy, et al.
Heliyon
Other Activities
Small Projects
Some smaller projects I worked on during my master's.
Constructing A Neural Network by Hand
Building and training a neural network from scratch and visualizing its predictions.
Bootstrap Hypothesis Testing for Quantiles
Hypothesis testing for quantiles using bootstrapping for p-value computation.
DNA sequence classification via an EM algorithm
Implementing the SeqEM algorithm, which allows to identify genetic variations in a genome, by hand.
Web Scraping Bot in Python
Implementation of a web scraping bot to extract real estate listings.
Education
- PhD in Computer Science
University of Luxembourg
2023-current - MSc in Applied Mathematics, Statistics
University of Strasbourg, France
2019-2021 - Double Major BSc in Mathematics and Economics
University of Strasbourg, France
2016-2019