Learned classifiers for selecting optimal prompting strategies in multilingual LLMs outperform fixed approaches, generalize to new tasks, and show benefits driven primarily by language resource levels rather than translation quality.
InProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 18761–18799, Vienna, Austria
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs
Learned classifiers for selecting optimal prompting strategies in multilingual LLMs outperform fixed approaches, generalize to new tasks, and show benefits driven primarily by language resource levels rather than translation quality.