mlsanityData to 14 Oct 2026

Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA

arXiv 2604.05387 ↗First posted 7 Apr 2026cs.IR cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have been incorporated into numerous industrial applications. Meanwhile, a vast array of API assets is scattered across various functions in the financial domain. An online financial question-answering system can leverage both LLMs and private APIs to provide timely financial analysis and information. The key is equipping the LLM model with function calling capability tailored to a financial scenario. However, a generic LLM requires customized financial APIs to call and struggles to adapt to the financial domain. Additionally, online user queries are diverse and contain out-of-distribution parameters compared with the required function input parameters, which makes it more difficult for a generic LLM to serve online users. In this paper, we propose a data-driven pipeline to enhance function calling in LLM for our online, deployed financial QA, comprising dataset construction, data augmentation, and model training. Specifically, we construct a dataset based on a previous study and update it periodically, incorporating queries and an augmentation method named AugFC. The addition of user query-related samples will textitexploit our financial toolset in a data-driven manner, and AugFC explores the possible parameter values to enhance the diversity of our updated dataset. Then, we train an LLM with a two-step method, which enables the use of our financial functions. Extensive experiments on existing offline datasets, as well as the deployment of an online scenario, illustrate the superiority of our pipeline. The related pipeline has been adopted in the financial QA of YuanBaofootnotehttps://yuanbao.tencent.com/chat/, one of the largest chat platforms in China.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 39 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

21 of 39 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2023Qwen Technical Reportcited by 3,344
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  9. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  10. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  11. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 393
  12. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 198
9 more
  1. 2024FinBen: A Holistic Financial Benchmark for Large Language Modelscited by 141
  2. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agentscited by 56
  3. 2024FinTextQA: A Dataset for Long-form Financial Question Answeringcited by 54
  4. 2025ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Usecited by 50
  5. 2025FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challengingcited by 28
  6. 2024Enhancing Financial Question Answering with a Multi-Agent Reflection Frameworkcited by 12
  7. 2024Fine-tuning Smaller Language Models for Question Answering over Financial Documentscited by 8
  8. 2023Zero-Shot Question Answering over Financial Documents using Large Language Modelscited by 7
  9. 2024Adaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipelinecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models
  2. 2024FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models
  3. 2024Equipping Language Models with Tool Use Capability for Tabular Data Analysis in Finance
  4. 2023Data-Centric Financial Large Language Models
  5. 2025Evaluating Large Language Models for Financial Reasoning: A CFA-Based Benchmark Study
  6. 2025FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API
  7. 2023Beyond Classification: Financial Reasoning in State-of-the-Art Language Models
  8. 2025QuantMCP: Grounding Large Language Models in Verifiable Financial Reality