ORPO fine-tuning, which explicitly penalizes disfavored language-mixed responses, nearly eliminates language confusion in Korean-generation LLMs without hurting QA accuracy.
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
-
Controlling Language Confusion in Multilingual LLMs
ORPO fine-tuning, which explicitly penalizes disfavored language-mixed responses, nearly eliminates language confusion in Korean-generation LLMs without hurting QA accuracy.