A benchmark of 809 yokai questions shows Japanese-centric LLMs, particularly Llama-3-based continual pretraining models, outperform English-centric models on Japanese folktale knowledge.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales
A benchmark of 809 yokai questions shows Japanese-centric LLMs, particularly Llama-3-based continual pretraining models, outperform English-centric models on Japanese folktale knowledge.