作者位次 #5/11ACL 2026Findings· Findings of ACL
F in T ool S yn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
Caishuang Huang · Yang Qiao · Rongyu Zhang · Junjie Ye · Pu Lu · Wuwenxi · Meng Zhou · Xiku Du · Qi Zhang · Tao Gui · Xuanjing Huang
摘要
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....