A Japanese safety dataset with reference answers improves LLM safety through fine-tuning and provides a benchmark that reveals large safety differences across 12 models.
Investigating tuning methods for achieving usefulness and safety for Japanese large language models (in Japanese)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
AnswerCarefully: A Dataset for Improving the Safety of Japanese LLM Output
A Japanese safety dataset with reference answers improves LLM safety through fine-tuning and provides a benchmark that reveals large safety differences across 12 models.