FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design

• URL: http://arxiv.org/abs/2506.13066v1
• Date: Mon, 16 Jun 2025 03:19:31 GMT
• Title: FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design
• Authors: Kai Lan, Jiayong Zhu, Jiangtong Li, Dawei Cheng, Guang Chen, Changjun Jiang,
• Abstract summary: FinLMM-R1 combines an automated and scalable pipeline for data construction with enhanced training strategies to improve the multimodal reasoning of LMM.<n>We collect 89,378 aligned image-question pairs from 23,397 financial reports, covering tasks such as arithmetic reasoning, statistics reasoning, financial explanation, and financial knowledge.<n>In the first stage, we focus on text-only tasks with format and accuracy rewards to guide the model in generating well-structured thinking contents.<n>In the second stage, we construct multi-image contrastive samples with additional reward components including image selection, thinking content length, and adversarial reward.
• Score: 21.582176552307974
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Multimodal Models (LMMs) demonstrate significant cross-modal reasoning capabilities. However, financial applications face challenges due to the lack of high-quality multimodal reasoning datasets and the inefficiency of existing training paradigms for reasoning enhancement. To address these issues, we propose an integrated framework, FinLMM-R1, combining an automated and scalable pipeline for data construction with enhanced training strategies to improve the multimodal reasoning of LMM. The Automated and Scalable Pipeline (ASP) resolves textual-visual misalignment in financial reports through a separate paradigm of question-answer generation and image-question alignment, ensuring data integrity and extraction efficiency. Through ASP, we collect 89,378 aligned image-question pairs from 23,397 financial reports, covering tasks such as arithmetic reasoning, statistics reasoning, financial explanation, and financial knowledge. Moreover, we introduce the Thinking with Adversarial Reward in LMM (TAR-LMM), extending the prior two-stage training framework [1] with additional reward mechanisms. In the first stage, we focus on text-only tasks with format and accuracy rewards to guide the model in generating well-structured thinking contents. In the second stage, we construct multi-image contrastive samples with additional reward components including image selection, thinking content length, and adversarial reward to jointly optimize the LMM across visual perception, reasoning efficiency, and logical coherence. Extensive experiments on 7 benchmarks show ASP-derived dataset and training framework significantly improve answer accuracy and reasoning depth over existing reasoning LMMs in both general and financial multimodal contexts.

Related papers

• ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding [65.16833684071715]
  Think Omni is a training-free and data-free framework that lifts textual reasoning to omni-modal scenarios.<n> Experiments on six multi-modal reasoning benchmarks demonstrate that Think Omni consistently delivers performance improvements.
  arXiv  Detail & Related papers  (2026-02-26T18:10:41Z)
• Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition [51.68340973140949]
  Multimodal Named Entity Recognition (GMNER) aims to extract text-based entities, assign them semantic categories, and ground them to corresponding visual regions.<n> MLLMs exhibit $textbfmodality bias$, including visual bias and textual bias, which stems from their tendency to take unimodal shortcuts.<n>We propose Modality-aware Consistency Reasoning ($bfMCR$), which enforces structured cross-modal reasoning.
  arXiv  Detail & Related papers  (2026-02-04T12:12:49Z)
• FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation [15.654001393123403]
  FinMTM is a multi-turn multimodal benchmark that expands diversity along both data and task dimensions.<n>On the data side, we curate and annotate 11,133 bilingual (Chinese and English) financial QA pairs grounded in financial visuals.<n>On the task side, FinMTM covers single- and multiple-choice questions, multi-turn open-ended dialogues, and agent-based tasks.
  arXiv  Detail & Related papers  (2026-02-03T05:38:24Z)
• MMhops-R1: Multimodal Multi-hop Reasoning [89.68086555694084]
  We introduce MMhops, a novel benchmark designed to evaluate and foster multi-modal multi-hop reasoning.<n> MMhops dataset comprises two challenging task formats, Bridging and Comparison.<n>We propose MMhops-R1, a novel multi-modal Retrieval-Augmented Generation framework for dynamic reasoning.
  arXiv  Detail & Related papers  (2025-12-15T17:29:02Z)
• 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)
• CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model [21.702901343472558]
  Multimodal Large Language Models (MLLMs) have rapidly evolved with the growth of Large Language Models (LLMs)<n>In this paper, we introduce CFBenchmark-MM, a Chinese multimodal financial benchmark with over 9,000 image-question pairs featuring tables, histogram charts, line charts, pie charts, and structural diagrams.<n>We develop a staged evaluation system to assess MLLMs in handling multimodal information by providing different visual content step by step.
  arXiv  Detail & Related papers  (2025-06-16T02:52:44Z)
• Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models [45.15161506154318]
  Infi-MMR is a framework to systematically unlock the reasoning potential of Multimodal Small Language Models.<n>The first phase, Foundational Reasoning Activation, leverages high-quality textual reasoning datasets to activate and strengthen the model's logical reasoning capabilities.<n>The second phase, Cross-Modal Reasoning Adaptation, utilizes caption-augmented multimodal data to facilitate the progressive transfer of reasoning skills to multimodal contexts.<n>The third phase, Multimodal Reasoning Enhancement, employs curated, caption-free multimodal data to mitigate linguistic biases and promote robust cross-modal reasoning.
  arXiv  Detail & Related papers  (2025-05-29T04:51:56Z)
• Visualizing Thought: Conceptual Diagrams Enable Robust Planning in LMMs [59.66595230543127]
  Conceptual diagrams externalize mental models, abstracting irrelevant details to efficiently capture how entities interact.<n>Large Language Models (LLMs) and Large MultiModal Models (LMMs) predominantly reason through text.<n>We propose Visual Thinking, a generalizable framework that enables LMMs to reason through multiple chains of self-generated conceptual diagrams.
  arXiv  Detail & Related papers  (2025-03-14T18:27:02Z)
• LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL [32.67667242745463]
  We propose a two-stage framework adapting rule-based RL for multimodal reasoning through textbfFoundational Reasoning Enhancement (FRE) followed by textbfMultimodal Generalization Training (MGT).<n>Experiments on Qwen2.5-VL-Instruct-3B demonstrate that LMM-R1 achieves 4.83% and 4.5% average improvements over baselines in multimodal and text-only benchmarks, respectively, with a 3.63% gain in complex Football Game tasks.
  arXiv  Detail & Related papers  (2025-03-10T17:04:14Z)
• MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency [63.23935582919081]
  Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs)<n>We introduce MME-CoT, a specialized benchmark evaluating the CoT reasoning performance of LMMs.<n>We conduct an in-depth analysis of state-of-the-art LMMs, uncovering several key insights.
  arXiv  Detail & Related papers  (2025-02-13T18:59:46Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation [92.73405185996315]
  Large Multimodal Models (LMMs) have demonstrated impressive capabilities in multimodal understanding and generation.<n>Existing approaches, such as layout planning for multi-step generation and learning from human feedback or AI feedback, depend heavily on prompt engineering.<n>We introduce a model-agnostic iterative self-feedback framework (SILMM) that can enable LMMs to provide helpful and scalable self-improvement and optimize text-image alignment.
  arXiv  Detail & Related papers  (2024-12-08T05:28:08Z)
• Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models [64.1799100754406]
  Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more.<n>Despite various efforts to improve LLM reasoning, high-quality long-chain reasoning data and optimized training pipelines still remain inadequately explored in vision-language tasks.<n>We present Insight-V, an early effort to 1) scalably produce long and robust reasoning data for complex multi-modal tasks, and 2) an effective training pipeline to enhance the reasoning capabilities of MLLMs.
  arXiv  Detail & Related papers  (2024-11-21T18:59:55Z)
• The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio [118.75449542080746]
  This paper presents the first systematic investigation of hallucinations in large multimodal models (LMMs) Our study reveals two key contributors to hallucinations: overreliance on unimodal priors and spurious inter-modality correlations. Our findings highlight key vulnerabilities, including imbalances in modality integration and biases from training data, underscoring the need for balanced cross-modal learning.
  arXiv  Detail & Related papers  (2024-10-16T17:59:02Z)
• CatMemo at the FinLLM Challenge Task: Fine-Tuning Large Language Models using Data Fusion in Financial Applications [10.225210627594894]
  This paper presents our solution to IJCAI-2024 FinLLM challenge, investigating the capabilities of LLMs within three critical areas of financial tasks. Financial classification, financial text summarization, and single stock trading are investigated. Our approach aims to tackle these diverse tasks in a comprehensive and integrated manner, showcasing LLMs' capacity to address diverse and complex financial tasks with improved accuracy and decision-making capabilities.
  arXiv  Detail & Related papers  (2024-07-02T05:04:13Z)
• Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems [57.41621687431203]
  Large language models (LLMs) and foundation models have been recently touted as a game-changer for 6G systems. This paper presents a comprehensive vision on how to design universal foundation models tailored towards the deployment of artificial intelligence (AI)-native networks.
  arXiv  Detail & Related papers  (2024-01-30T00:21:41Z)

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.