2025
LongTail-Swap: benchmarking language models’ abilities on rare words
Robin Algayres, Charles-{\'E}ric Saint-James, Mahi Luthra, Jiayi Shen, Youssef Benchekroun, Dongyan Lin +3
EMNLP 2025
Children learn to speak with a low amount of data and can be taught new words on a few-shot basis, making them particularly data-efficient learners. The BabyLM challenge aims at exploring language model (LM) training in the low-data regime but uses metrics that concentrate on the head of the word di