When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use
英文标题：When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use
arXiv:2608.11715v1 Announce Type: new Abstract: The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the correct tool but generates argument values in an inconsistent language, which we term Argument Language
打开原文相关 4.8 · 机会 3
2.1 KB
640 B
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2608.11715v1 Announce Type: new Abstract: The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the correct tool but generates argument values in an inconsistent language, which we term Argument Language
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×