QianfanHuijin Technical Report: A Novel Multi-Stage Training Paradigm for Finance Industrial LLMs

• URL: http://arxiv.org/abs/2512.24314v1
• Date: Tue, 30 Dec 2025 16:10:51 GMT
• Title: QianfanHuijin Technical Report: A Novel Multi-Stage Training Paradigm for Finance Industrial LLMs
• Authors: Shupeng Li, Weipeng Lu, Linyun Liu, Chen Lin, Shaofei Li, Zhendong Tan, Hanjun Zhong, Yucheng Zeng, Chenghao Zhu, Mengyue Liu, Daxiang Dong, Jianmin Wu, Yunting Xiao, Annan Li, Danyu Liu, Jingnan Zhang, Licen Liu, Dawei Yin, Dou Shen,
• Abstract summary: We present QianfanHuijin, a financial domain LLM, and propose a generalizable multi-stage training paradigm for industrial model enhancement.<n>Our approach begins with Continual Pre-training (CPT) on financial corpora to consolidate the knowledge base.<n>This is followed by a fine-grained Post-training pipeline designed with increasing specificity: starting with Financial SFT, progressing to Finance Reasoning RL and Finance Agentic RL, and culminating in General RL.
• Score: 30.6564068779509
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Domain-specific enhancement of Large Language Models (LLMs) within the financial context has long been a focal point of industrial application. While previous models such as BloombergGPT and Baichuan-Finance primarily focused on knowledge enhancement, the deepening complexity of financial services has driven a growing demand for models that possess not only domain knowledge but also robust financial reasoning and agentic capabilities. In this paper, we present QianfanHuijin, a financial domain LLM, and propose a generalizable multi-stage training paradigm for industrial model enhancement. Our approach begins with Continual Pre-training (CPT) on financial corpora to consolidate the knowledge base. This is followed by a fine-grained Post-training pipeline designed with increasing specificity: starting with Financial SFT, progressing to Finance Reasoning RL and Finance Agentic RL, and culminating in General RL aligned with real-world business scenarios. Empirical results demonstrate that QianfanHuijin achieves superior performance across various authoritative financial benchmarks. Furthermore, ablation studies confirm that the targeted Reasoning RL and Agentic RL stages yield significant gains in their respective capabilities. These findings validate our motivation and suggest that this fine-grained, progressive post-training methodology is poised to become a mainstream paradigm for various industrial-enhanced LLMs.

Related papers

• The LLM Pro Finance Suite: Multilingual Large Language Models for Financial Applications [4.211847212372977]
  The LLM Pro Finance Suite is a collection of five instruction-tuned large language models (LLMs) specifically designed for financial applications.<n>Our approach focuses on enhancing generalist instruction-tuned models, leveraging their existing strengths in instruction following, reasoning, and toxicity control.<n>We evaluate the Suite on a comprehensive financial benchmark suite, demonstrating consistent improvement over state-of-the-art baselines in finance-oriented tasks and financial translation.
  arXiv  Detail & Related papers  (2025-11-07T11:08:31Z)
• FinSight: Towards Real-World Financial Deep Research [68.31086471310773]
  FinSight is a novel framework for producing high-quality, multimodal financial reports.<n>To ensure professional-grade visualization, we propose an Iterative Vision-Enhanced Mechanism.<n>A two-stage Writing Framework expands concise Chain-of-Analysis segments into coherent, citation-aware, and multimodal reports.
  arXiv  Detail & Related papers  (2025-10-19T14:05:35Z)
• Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning [12.548390779247987]
  We introduce the Agentar-Fin-R1 series of financial large language models.<n>Our optimization approach integrates a high-quality, systematic financial task label system.<n>Our models undergo comprehensive evaluation on mainstream financial benchmarks.
  arXiv  Detail & Related papers  (2025-07-22T17:52:16Z)
• General-Reasoner: Advancing LLM Reasoning Across All Domains [64.70599911897595]
  Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs)<n>We propose General-Reasoner, a novel training paradigm designed to enhance LLM reasoning capabilities across diverse domains.<n>We train a series of models and evaluate them on a wide range of datasets covering wide domains like physics, chemistry, finance, electronics etc.
  arXiv  Detail & Related papers  (2025-05-20T17:41:33Z)
• Bridging Language Models and Financial Analysis [49.361943182322385]
  The rapid advancements in Large Language Models (LLMs) have unlocked transformative possibilities in natural language processing.<n>Financial data is often embedded in intricate relationships across textual content, numerical tables, and visual charts.<n>Despite the fast pace of innovation in LLM research, there remains a significant gap in their practical adoption within the finance industry.
  arXiv  Detail & Related papers  (2025-03-14T01:35:20Z)
• Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance [35.617409883103335]
  FinReason is the first financial reasoning benchmark covering multi-table analysis, long-context reasoning, and equation-based tasks.<n>We introduce FinCoT, the first open high-fidelity CoT corpus for finance, distilled from seven QA datasets.<n>We develop Fin-o1, the first open financial reasoning models trained via supervised fine-tuning and GRPO-based RL.
  arXiv  Detail & Related papers  (2025-02-12T05:13:04Z)
• Demystifying Domain-adaptive Post-training for Financial LLMs [87.28855088465197]
  FINDAP is a systematic and fine-grained investigation into domain-adaptive post-training of large language models.<n>Our approach consists of four key components: FinCap, FinRec, FinTrain and FinEval.<n>The resulting model, Llama-Fin, achieves, state-of-the-art performance across a wide range of financial tasks.
  arXiv  Detail & Related papers  (2025-01-09T04:26:15Z)
• A Review of Reinforcement Learning in Financial Applications [12.813502592542388]
  Reinforcement Learning (RL) has shown great potential to solve decision-making tasks in finance. We identify challenges including explainability, Markov Decision Process (MDP) modeling, and robustness that hinder the broader utilization of RL in the financial industry. We propose future research directions, such as benchmarking, contextual RL, multi-agent RL, and model-based RL.
  arXiv  Detail & Related papers  (2024-11-01T01:03:10Z)
• Financial Knowledge Large Language Model [4.599537455808687]
  We introduce IDEA-FinBench, an evaluation benchmark for assessing financial knowledge in large language models (LLMs) We propose IDEA-FinKER, a framework designed to facilitate the rapid adaptation of general LLMs to the financial domain. Finally, we present IDEA-FinQA, a financial question-answering system powered by LLMs.
  arXiv  Detail & Related papers  (2024-06-29T08:26:49Z)
• A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges [60.546677053091685]
  Large language models (LLMs) have unlocked novel opportunities for machine learning applications in the financial domain. We explore the application of LLMs on various financial tasks, focusing on their potential to transform traditional practices and drive innovation. We highlight this survey for categorizing the existing literature into key application areas, including linguistic tasks, sentiment analysis, financial time series, financial reasoning, agent-based modeling, and other applications.
  arXiv  Detail & Related papers  (2024-06-15T16:11:35Z)
• FinBen: A Holistic Financial Benchmark for Large Language Models [75.09474986283394]
  FinBen is the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading.
  arXiv  Detail & Related papers  (2024-02-20T02:16:16Z)
• FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative Finance [58.77314662664463]
  FinRL-Meta builds a universe of market environments for data-driven financial reinforcement learning. First, FinRL-Meta separates financial data processing from the design pipeline of DRL-based strategy. Second, FinRL-Meta provides hundreds of market environments for various trading tasks.
  arXiv  Detail & Related papers  (2021-12-13T16:03:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.