Siddharth Chauhan

When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use

It is found that, in this benchmark, supervised fine-tuning (SFT) provides a strong baseline, substantially improving argument language consistency and end-to-end function call accuracy and, under consistent model selection, SFT achieves performance comparable to, and sometimes exceeding more complex reinforcement learning (RL) approaches.