๐ŸŽ“ ๐——๐—ถ๐˜€๐˜€๐—ฒ๐—ฟ๐˜๐—ฎ๐˜๐—ถ๐—ผ๐—ป ๐——๐—ฒ๐—ณ๐—ฒ๐—ป๐˜€๐—ฒ โ€“ ๐—–๐—ฒ๐—ฐ๐—ถ๐—น๐—ถ๐—ฎ
Congratulations to Chen Cecilia Liu on the successful PhD defense at the UKP Lab of Technische Universitรคt Darmstadt.

In her thesis ๐˜Ž๐˜ฆ๐˜ฏ๐˜ฆ๐˜ณ๐˜ข๐˜ญ๐˜ช๐˜ป๐˜ข๐˜ต๐˜ช๐˜ฐ๐˜ฏ ๐˜ข๐˜ฏ๐˜ฅ ๐˜ˆ๐˜ฅ๐˜ข๐˜ฑ๐˜ต๐˜ข๐˜ต๐˜ช๐˜ฐ๐˜ฏ ๐˜ฐ๐˜ง ๐˜“๐˜ข๐˜ฏ๐˜จ๐˜ถ๐˜ข๐˜จ๐˜ฆ ๐˜”๐˜ฐ๐˜ฅ๐˜ฆ๐˜ญ๐˜ด ๐˜ต๐˜ฐ ๐˜“๐˜ข๐˜ฏ๐˜จ๐˜ถ๐˜ข๐˜จ๐˜ฆ๐˜ด ๐˜ข๐˜ฏ๐˜ฅ ๐˜Š๐˜ถ๐˜ญ๐˜ต๐˜ถ๐˜ณ๐˜ฆ๐˜ด, Cecilia investigates ...

..how language models can better generalize across languages and adapt to cultural contexts. Combining parameter efficient fine tuning with insights from cultural learning theory, she shows how targeted training interventions can improve robustness and multilingual performance.

Her work further demonstrates how situated evaluation and social interaction settings can deepen our understanding of cultural competence in language models and help create more nuanced and context sensitive NLP systems.

Ceciliaโ€™s thesis marks a strong contribution to ๐—บ๐˜‚๐—น๐˜๐—ถ๐—น๐—ถ๐—ป๐—ด๐˜‚๐—ฎ๐—น ๐—ฎ๐—ป๐—ฑ ๐—ฐ๐˜‚๐—น๐˜๐˜‚๐—ฟ๐—ฎ๐—น๐—น๐˜† ๐—ฎ๐˜„๐—ฎ๐—ฟ๐—ฒ ๐—ก๐—Ÿ๐—ฃ. It is an important step toward more reliable and context sensitive language technologies.

๐Ÿ‘ฅ Jury: Iryna Gurevych (TU Darmstadt), Fajri Koto (MBZUAI (Mohamed bin Zayed University of Artificial Intelligence), Anna Rohrbach (TU Darmstadt), Justus Thies (TU Darmstadt)

๐Ÿ‘ Congratulations on this achievement and all the best for Ceciliaโ€™s new role as postdoctoral researcher at the University of Cambridge!

#NLP #PhDDefense #MultilingualAI #CulturalAI #LanguageModels #UKPLab #TUDarmstadt Computer Science, TU Darmstadt