Update README.md

README.md

@@ -54,4 +54,14 @@ The tokenizer is BPE-based (`GPTNeoXTokenizerFast`) with BERT-style special toke
 
 ## Citation
 
-A paper describing this model will be published soon. In the meantime, please cite this repository if you use this model in your work.
+Please cite this paper (preprint, accepted to ACL 2026 Findings) if you use this model in your work.
+
+@misc{plum2026ltzglueluxembourgishgenerallanguage,
+  title={ltzGLUE: Luxembourgish General Language Understanding Evaluation}, 
+  author={Alistair Plum and Felicia Körner and Anne-Marie Lutgen and Laura Bernardy and Fred Philippy and Emilia Milano and Nils Rehlinger and Cédric Lothritz and Tharindu Ranasinghe and Barbara Plank and Christoph Purschke},
+  year={2026},
+  eprint={2604.17976},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL},
+  url={https://arxiv.org/abs/2604.17976}, 
+}