ICL instruction following underperforms in small and multilingual models versus instruction tuning, with DPO offering partial gains but not closing the gap to large English models.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models
ICL instruction following underperforms in small and multilingual models versus instruction tuning, with DPO offering partial gains but not closing the gap to large English models.