@inproceedings{jiang-etal-2026-finmaster,
    title = "{F}in{M}aster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models",
    author = "Jiang, Junzhe  and
      Yang, Chang  and
      Cui, Aixin  and
      Jin, Sihan  and
      Zhang, Yujing  and
      Xiao, Yilin  and
      Wang, Ruiyu  and
      Li, Bo  and
      Huang, Xiao  and
      Sun, Danny Dongning  and
      Wang, Xinrun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.385/",
    pages = "7787--7844",
    ISBN = "979-8-89176-395-1",
    abstract = "Financial management is high-stakes, where small errors can propagate into reporting deviations and costly downstream decisions, yet real-world workflows remain labor-intensive and fragmented, and existing automation supports only isolated steps rather than complete workflows. Large language models (LLMs) show promise in automating financial workflows, but current benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow-level evaluation. To address these gaps, we present **FinMaster**, a benchmark for evaluating large language models on full financial management workflows spanning financial literacy, accounting, auditing, and consulting. **FinMaster** comprises three modules: *FinSim* generates synthetic datasets compliant with real-world accounting standards for diverse company types, enabling realistic evaluation without relying on proprietary financial records. *FinSuite* offers 183 tasks across core financial domains. *FinEval* provides a unified evaluation framework. Extensive experiments on state-of-the-art models including GPT-4o-mini, Claude-3.7-Sonnet, and DeepSeek-V3 reveal critical capability gaps in financial reasoning, with accuracy dropping from over 90{\%} on basic tasks to 40{\%} on complex scenarios requiring multi-step reasoning. This degradation reflects error propagation, where accuracy reaches 58{\%} for single-metric calculations but decreases to 37{\%} in multi-metric settings. **FinMaster** provides scalable and reproducible benchmarking for realistic end-to-end financial workflows, helping advance reliable deployment of LLMs in financial practice."
}