Financial Risk Relation Identification through Dual-view Adaptation

• URL: http://arxiv.org/abs/2509.18775v1
• Date: Tue, 23 Sep 2025 08:09:30 GMT
• Title: Financial Risk Relation Identification through Dual-view Adaptation
• Authors: Wei-Ning Chiu, Yu-Hsiang Wang, Andy Hsiao, Yu-Shiang Huang, Chuan-Ju Wang,
• Abstract summary: Inter-firm risk events can trigger ripple effects across firms.<n>Traditionally, such assessments rely on expert judgment and manual analysis.<n>We propose a systematic method for extracting inter-firm risk relations using Form 10-K filings.
• Score: 5.845450355216619
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A multitude of interconnected risk events -- ranging from regulatory changes to geopolitical tensions -- can trigger ripple effects across firms. Identifying inter-firm risk relations is thus crucial for applications like portfolio management and investment strategy. Traditionally, such assessments rely on expert judgment and manual analysis, which are, however, subjective, labor-intensive, and difficult to scale. To address this, we propose a systematic method for extracting inter-firm risk relations using Form 10-K filings -- authoritative, standardized financial documents -- as our data source. Leveraging recent advances in natural language processing, our approach captures implicit and abstract risk connections through unsupervised fine-tuning based on chronological and lexical patterns in the filings. This enables the development of a domain-specific financial encoder with a deeper contextual understanding and introduces a quantitative risk relation score for transparency, interpretable analysis. Extensive experiments demonstrate that our method outperforms strong baselines across multiple evaluation settings.

Related papers

• SHERLOCK: Towards Dynamic Knowledge Adaptation in LLM-enhanced E-commerce Risk Management [10.255396179168974]
  E-commerce companies conduct risk investigations into suspicious cases to identify emerging fraud patterns.<n>The sheer volume of case analyses imposes a substantial workload on risk management analysts.<n>We propose the SHERLOCK framework, which leverages the reasoning capabilities of large language models (LLMs) to assist analysts in risk investigations.
  arXiv  Detail & Related papers  (2025-10-10T02:57:58Z)
• RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration [81.38705556267917]
  Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations.<n>We introduce a theoretical framework that reconstructs the underlying risk concept space.<n>We propose RADAR, a multi-agent collaborative evaluation framework.
  arXiv  Detail & Related papers  (2025-09-28T09:35:32Z)
• Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation [51.19622266249408]
  MultiTrust-X is a benchmark for evaluating, analyzing, and mitigating the trustworthiness issues of MLLMs.<n>Based on the taxonomy, MultiTrust-X includes 32 tasks and 28 curated datasets.<n>Our experiments reveal significant vulnerabilities in current models.
  arXiv  Detail & Related papers  (2025-08-21T09:00:01Z)
• Explainable AI for Comprehensive Risk Assessment for Financial Reports: A Lightweight Hierarchical Transformer Network Approach [1.2200609701777907]
  Every publicly traded U.S. company files an annual 10-K report containing critical insights into financial health and risk.<n>We propose Tiny eXplainable Risk Assessor (TinyXRA), a transformer-based model that automatically assesses company risk from these reports.<n>TinyXRA incorporates skewness, kurtosis, and the Sortino ratio for more comprehensive risk assessment.
  arXiv  Detail & Related papers  (2025-06-30T12:13:35Z)
• Dynamic Hedging Strategies in Derivatives Markets with LLM-Driven Sentiment and News Analytics [30.815524322885754]
  This paper introduces a novel framework that leverages large language models (LLMs) for sentiment analysis and news analytics to inform hedging decisions.<n>The framework allows for real-time adjustments to hedging strategies, adapting positions based on continuous sentiment signals.
  arXiv  Detail & Related papers  (2025-04-05T22:35:06Z)
• Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients [0.0]
  This paper tackles the problem of mitigating catastrophic risk in a sequential decision making process. A policy gradient algorithm is developed, that we call POTPG. An application to financial risk management is presented.
  arXiv  Detail & Related papers  (2024-06-21T19:27:46Z)
• Data-Adaptive Tradeoffs among Multiple Risks in Distribution-Free Prediction [55.77015419028725]
  We develop methods that permit valid control of risk when threshold and tradeoff parameters are chosen adaptively. Our methodology supports monotone and nearly-monotone risks, but otherwise makes no distributional assumptions.
  arXiv  Detail & Related papers  (2024-03-28T17:28:06Z)
• Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks [62.94317686301643]
  Company financial risk is ubiquitous and early risk assessment for listed companies can avoid considerable losses. Traditional methods mainly focus on the financial statements of companies and lack the complex relationships among them. We propose a novel Hierarchical Graph Neural Network (TH-GNN) for Tribe-style graphs via two levels, with the first level to encode the structure pattern of the tribes with contrastive learning, and the second level to diffuse information based on the inter-tribe relations.
  arXiv  Detail & Related papers  (2023-01-31T09:17:13Z)
• Deep Learning for Systemic Risk Measures [3.274367403737527]
  The aim of this paper is to study a new methodological framework for systemic risk measures. Under this new framework, systemic risk measures can be interpreted as the minimal amount of cash that secures the aggregated system. Deep learning is increasingly receiving attention in financial modelings and risk management.
  arXiv  Detail & Related papers  (2022-07-02T05:01:19Z)
• Towards a multi-stakeholder value-based assessment framework for algorithmic systems [76.79703106646967]
  We develop a value-based assessment framework that visualizes closeness and tensions between values. We give guidelines on how to operationalize them, while opening up the evaluation and deliberation process to a wide range of stakeholders.
  arXiv  Detail & Related papers  (2022-05-09T19:28:32Z)
• Detecting data-driven robust statistical arbitrage strategies with deep neural networks [5.812554622073437]
  We present an approach, based on deep neural networks, that allows identifying robust statistical arbitrage strategies in financial markets. The presented novel methodology allows to consider a large amount of underlying securities simultaneously. We provide a method to build an ambiguity set of admissible probability measures that can be derived from observed market data.
  arXiv  Detail & Related papers  (2022-03-07T07:23:18Z)
• Stateful Offline Contextual Policy Evaluation and Learning [88.9134799076718]
  We study off-policy evaluation and learning from sequential data. We formalize the relevant causal structure of problems such as dynamic personalized pricing. We show improved out-of-sample policy performance in this class of relevant problems.
  arXiv  Detail & Related papers  (2021-10-19T16:15:56Z)
• Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning [100.73223416589596]
  We propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations. A new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-06T06:28:17Z)

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.