---
title: "Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models"
authors:
  - "Jie Zhu"
  - "Yuanchen Zhou"
  - "Shuo Jiang"
  - "Junhui Li"
  - "Lifan Guo"
  - "Feng Chen"
  - "Chi Zhang"
doi: "10.24963/ijcai.2026/683"
url: "https://ijcai.org/proceedings/2026/683"
pdf: "https://ijcai.org/proceedings/2026/0683.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6136-6144"
track: "Main Track"
keywords:
  - "Natural Language Processing: Resources and evaluation"
  - "Natural Language Processing: Other"
  - "Natural Language Processing: Language models"
---

# Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

Jie Zhu, Yuanchen Zhou, Shuo Jiang, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6136-6144. DOI: [10.24963/ijcai.2026/683](https://doi.org/10.24963/ijcai.2026/683)

## Abstract

Process Reward Models (PRMs) supervise intermediate reasoning steps in large language models (LLMs), but existing PRMs are mainly trained on general-domain data and struggle with the structured, symbolic, and fact-sensitive nature of financial reasoning. Financial tasks require not only correct final answers but also verifiable intermediate steps grounded in domain knowledge. In this paper, we propose Fin-PRM, a domain-specialized, trajectory-aware PRM for financial reasoning that jointly models step-level correctness and trajectory-level coherence, producing binary supervision signals for both local and global reasoning quality. To support reliable supervision, we construct a high-quality financial reasoning dataset of 3K trajectories, where step- and trajectory-level labels are automatically derived from multi-source reward signals, including Monte Carlo rollouts, LLM-based evaluation, and explicit financial knowledge verification. Fin-PRM defines a unified ranking score that integrates step- and trajectory-level rewards, enabling consistent use across multiple settings. We evaluate Fin-PRM in three scenarios: (1) offline trajectory selection for supervised fine-tuning, (2) reward-guided Best-of-N inference for test-time scaling, and (3) process-aware reward shaping for reinforcement learning. Experiments on financial reasoning benchmarks, including CFLUE and FinQA, show that Fin-PRM consistently outperforms general-purpose PRMs and strong baselines. Our project resources will be available at https://github.com/aliyun/qwen-dianjin.