Y-NQ: English-Yorùbá Evaluation dataset for Open-Book Reading Comprehension and Text Generation
This work addresses the need for evaluation resources in low-resource languages like Yorùbá, highlighting gaps in LLM capabilities, though it is incremental as it primarily provides a new dataset.
The authors introduced an English-Yorùbá evaluation dataset for open-book reading comprehension and text generation, revealing a consistent performance disparity where Yorùbá lags behind English, with a 2.5x drop in performance for comparable document lengths.
The purpose of this work is to share an English-Yorùbá evaluation dataset for open-book reading comprehension and text generation to assess the performance of models both in a high- and a low- resource language. The dataset contains 358 questions and answers on 338 English documents and 208 Yorùbá documents. The average document length is ~ 10k words for English and 430 words for Yorùbá. Experiments show a consistent disparity in performance between the two languages, with Yorùbá falling behind English for automatic metrics even if documents are much shorter for this language. For a small set of documents with comparable length, performance of Yorùbá drops by x2.5 times. When analyzing performance by length, we observe that Yorùbá decreases performance dramatically for documents that reach 1500 words while English performance is barely affected at that length. Our dataset opens the door to showcasing if English LLM reading comprehension capabilities extend to Yorùbá, which for the evaluated LLMs is not the case.