People
Sandra worked on NLP, representation learning and hallucination detection in language models. She holds a PhD from KU Leuven.
Projects
Language preference and hallucination in multilingual retrieval-augmented generation
Do language models prefer some languages over others when answering from documents? We test this for chatbots that answer questions from a collection of documents in several languages.
Research
2026
Detecting misinformation and machine-generated text
Developed and tested ways to detect misleading content and text written by language models. Produced the BUST benchmark.
Research
2023
Conversational recommendation of performers
With Stagend, improved a platform that matches performers to events, using multilingual question answering to fill in missing information.
Applied
2019–2020
· Industry
Publications with the group
Are Language Models Script-Aware?
AACL-IJCNLP 2026, 2026
Script Choice in LLMs: Evidence for Late-Layer Commitment
Findings of EMNLP 2026, Budapest, Hungary, 2026
Are the LLMs Capable of Maintaining at Least the Language Genus?
Proceedings of the Thirty-Second Language Resources and Evaluation Conference (LREC 2026), 2026
Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), 2025
Presenting LLMs' Collective Intelligence Approach for Multilingual Hallucination Detection
Proceedings of the 9th edition of the Swiss Text Analytics Conference, 2025
Joint Proceedings of the Thematic Workshops at Ital-IA 2025, Trieste, Italy, June 23-24, 2025, 2025
Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024, 2024