AIML-TUDA/SLR-Bench-Dutch

SLR-Bench-Dutch 是原始 SLR-Bench 数据集的荷兰语版本。它遵循相同的符号结构、评估框架和课程设置，但将所有自然语言任务提示翻译成荷兰语。这使得可以对荷兰语中的大型语言模型（LLMs）进行系统性的逻辑推理评估和训练，支持多语言推理和跨语言泛化研究。SLR-Bench-Dutch is the Dutch-language counterpart of the original SLR-Bench dataset. It follows the same symbolic structure, evaluation framework, and curriculum as the English version but provides all natural-language task prompts translated into Dutch. This enables systematic evaluation and training of Large Language Models (LLMs) in logical reasoning in Dutch, supporting both multilingual reasoning and cross-lingual generalization research.