On a new multilingual function-calling benchmark, supervised fine-tuning largely resolves argument language mismatch, and reinforcement learning adds targeted but incremental gains.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use
On a new multilingual function-calling benchmark, supervised fine-tuning largely resolves argument language mismatch, and reinforcement learning adds targeted but incremental gains.