@inproceedings{umutlu-etal-2025-evaluating, title = "Evaluating the Quality of Benchmark Datasets for Low-Resource Languages: A Case Study on {T}urkish", author = "Umutlu, Elif Ecem and Cengiz, Ayse Aysu and Sever, Ahmet Kaan and Erdem, Seyma and Aytan, Burak and Tufan, Busra and Topraksoy, Abdullah and Dar{\i}c{\i}, Esra and Toraman, Cagri", editor = "Arviv, Ofir and Clinciu, Miruna and Dhole, Kaustubh and Dror, Rotem and Gehrmann, Sebastian and Habba, Eliya and Itzhak, Itay and Mille, Simon and Perlitz, Yotam and Santus, Enrico and Sedoc, Jo{\~a}o and Shmueli Scheuer, Michal and Stanovsky, Gabriel and Tafjord, Oyvind", booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})", month = jul, year = "2025", address = "Vienna, Austria and virtual meeting", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/metadata-correction-jian-chen-ub/2025.gem-1.41/", pages = "471--487", ISBN = "979-8-89176-261-9" }