FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
This addresses the need for high-quality, implicit tool-use data in finance, offering a domain-specific solution with incremental improvements over existing synthesis methods.
The paper tackled the problem of generating realistic financial dialogue data for LLM tool-use by introducing FinToolSyn, a forward synthesis framework that produced over 148k dialogue instances with dynamic tool retrieval, leading to a 21.06% improvement in model performance.
Tool-use capabilities are vital for Large Language Models (LLMs) in finance, a domain characterized by massive investment targets and data-intensive inquiries. However, existing data synthesis methods typically rely on a reverse synthesis paradigm, generating user queries from pre-sampled tools. This approach inevitably introduces artificial explicitness, yielding queries that fail to capture the implicit, event-driven nature of real-world needs. Moreover, its reliance on static tool sets overlooks the dynamic retrieval process required to navigate massive tool spaces. To address these challenges, we introduce \textit{FinToolSyn}, a forward synthesis framework designed to generate high-quality financial dialogues. Progressing from persona instruction and atomic tool synthesis to dynamic retrieval dialogue generation, our pipeline constructs a repository of 43,066 tools and synthesizes over 148k dialogue instances, incorporating dynamic retrieval to emulate the noisy candidate sets typical of massive tool spaces. We also establish a dedicated benchmark to evaluate tool-calling capabilities in realistic financial scenarios. Extensive experiments demonstrate that models trained on FinToolSyn achieve a 21.06\% improvement, providing a robust foundation for tool learning in financial scenarios.