Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation
This work addresses the challenge of improving autonomous agents' tool usage in LLMs, particularly for multilingual applications, though it appears incremental by building on existing function-calling methods.
This research tackled the problem of enhancing function-calling capabilities in large language models by exploring strategies like prompt formats, data integration, and multilingual translation, resulting in improved accuracy and relevance detection, with significant gains demonstrated in Traditional Chinese.
Large language models (LLMs) have significantly advanced autonomous agents, particularly in zero-shot tool usage, also known as function calling. This research delves into enhancing the function-calling capabilities of LLMs by exploring different approaches, including prompt formats for integrating function descriptions, blending function-calling and instruction-following data, introducing a novel Decision Token for conditional prompts, leveraging chain-of-thought reasoning, and overcoming multilingual challenges with a translation pipeline. Our key findings and contributions are as follows: (1) Instruction-following data improves both function-calling accuracy and relevance detection. (2) The use of the newly proposed Decision Token, combined with synthetic non-function-call data, enhances relevance detection. (3) A tailored translation pipeline effectively overcomes multilingual limitations, demonstrating significant improvements in Traditional Chinese. These insights highlight the potential for improved function-calling capabilities and multilingual applications in LLMs.