Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation

2024/12/02 by Yi-Chang Chen, Chen, Yi-Chang, Po‐Chun Hsu +5 · 6 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques

paper · pdf · doi:10.48550/arxiv.2412.01130

openalex publication_date 2024/12/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling Agents
• Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents
• Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
• Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making
• MCP-Enabled LLM for Meta-optics Inverse Design: Leveraging Differentiable Solver without LLM Expertise
• Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use

Related

• Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following
• Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
• Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMs
• Are LLMs Effective Backbones for Fine-tuning? An Experimental Investigation of Supervised LLMs on Chinese Short Text Matching
• Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe