Who Sees the Risk? Stakeholder Conflicts and Explanatory Policies in LLM-based Risk Assessment

• URL: http://arxiv.org/abs/2511.03152v1
• Date: Wed, 05 Nov 2025 03:19:21 GMT
• Title: Who Sees the Risk? Stakeholder Conflicts and Explanatory Policies in LLM-based Risk Assessment
• Abstract summary: This paper presents a framework for stakeholder-grounded risk assessment by using LLMs.<n>Using the Risk Atlas Nexus and GloVE explanation method, our framework generates stakeholder-specific, interpretable policies.<n>We demonstrate our method using three real-world AI use cases of medical AI, autonomous vehicles, and fraud detection domain.
• Score: 7.295206349432321
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding how different stakeholders perceive risks in AI systems is essential for their responsible deployment. This paper presents a framework for stakeholder-grounded risk assessment by using LLMs, acting as judges to predict and explain risks. Using the Risk Atlas Nexus and GloVE explanation method, our framework generates stakeholder-specific, interpretable policies that shows how different stakeholders agree or disagree about the same risks. We demonstrate our method using three real-world AI use cases of medical AI, autonomous vehicles, and fraud detection domain. We further propose an interactive visualization that reveals how and why conflicts emerge across stakeholder perspectives, enhancing transparency in conflict reasoning. Our results show that stakeholder perspectives significantly influence risk perception and conflict patterns. Our work emphasizes the importance of these stakeholder-aware explanations needed to make LLM-based evaluations more transparent, interpretable, and aligned with human-centered AI governance goals.

Related papers

• Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond [12.71451765578818]
  The society and emerging risk-based regulatory frameworks for AI underscore the need for rigorous risk assessment.<n>The paper highlights best practices and illuminates methodological gaps, highlighting areas for further research on AI risk assessment.
  arXiv  Detail & Related papers  (2026-07-02T14:04:56Z)
• Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework [63.74295981594549]
  Large language models (LLMs) engage in behaviors that serve their own objectives.<n>These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking.<n>We introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
  arXiv  Detail & Related papers  (2026-04-23T23:44:01Z)
• Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5 [61.787178868669265]
  This technical report presents an updated and granular assessment of five critical dimensions: cyber offense, persuasion and manipulation, strategic deception, uncontrolled AI R&D, and self-replication.<n>This work reflects our current understanding of AI frontier risks and urges collective action to mitigate these challenges.
  arXiv  Detail & Related papers  (2026-02-16T04:30:06Z)
• Toward a Unified Security Framework for AI Agents: Trust, Risk, and Liability [2.8407281360114527]
  The Trust, Risk and Liability (TRL) framework proposed in this paper ties together the interdependent relationships of trust, risk, and liability to provide a systematic method of building and enhancing trust.<n>The implications of the TRL framework lie in its potential societal impacts, economic impacts, ethical impacts, and more.<n>It is expected to bring remarkable values to addressing potential challenges and promoting trustworthy, risk-free, and responsible usage of AI in 6G networks.
  arXiv  Detail & Related papers  (2025-09-18T01:55:03Z)
• An Overview of the Risk-based Model of AI Governance [0.0]
  The 'Analysis' section proposes several criticisms of the risk based approach to AI governance.<n>It argues that the notion of risk is problematic as its inherent normativity reproduces dominant and harmful narratives about whose interests matter.<n>This paper concludes with the suggestion that existing risk governance scholarship can provide valuable insights toward the improvement of the risk based AI governance.
  arXiv  Detail & Related papers  (2025-07-21T06:56:04Z)
• Envisioning Stakeholder-Action Pairs to Mitigate Negative Impacts of AI: A Participatory Approach to Inform Policy Making [2.981139602986498]
  The potential for negative impacts of AI has rapidly become more pervasive around the world.<n>This has intensified a need for responsible AI governance.<n> Ensuring that AI policies align with democratic expectations requires methods that prioritize the voices and needs of those impacted.
  arXiv  Detail & Related papers  (2025-01-24T22:57:18Z)
• Perception Gaps in Risk, Benefit, and Value Between Experts and Public Challenge Socially Accepted AI [0.0]
  This study examines how the general public and academic AI experts perceive AI's capabilities and impact.<n>The scenarios span domains such as sustainability, healthcare, job performance, societal inequality, art, and warfare.<n>Experts consistently anticipate higher probabilities, perceive lower risks, report greater benefits, and express more positive sentiment toward AI compared to the non-experts.
  arXiv  Detail & Related papers  (2024-12-02T12:51:45Z)
• Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs [55.74117540987519]
  This paper explores the problem of commonsense level vision-knowledge conflict in Multimodal Large Language Models (MLLMs)<n>We introduce an automated framework, augmented with human-in-the-loop quality control, to generate inputs designed to simulate and evaluate these conflicts in MLLMs.<n>Using this framework, we have crafted a diagnostic benchmark consisting of 374 original images and 1,122 high-quality question-answer pairs.
  arXiv  Detail & Related papers  (2024-10-10T17:31:17Z)
• AI Risk Management Should Incorporate Both Safety and Security [185.68738503122114]
  We argue that stakeholders in AI risk management should be aware of the nuances, synergies, and interplay between safety and security. We introduce a unified reference framework to clarify the differences and interplay between AI safety and AI security.
  arXiv  Detail & Related papers  (2024-05-29T21:00:47Z)
• Mapping LLM Security Landscapes: A Comprehensive Stakeholder Risk Assessment Proposal [0.0]
  We propose a risk assessment process using tools like the risk rating methodology which is used for traditional systems. We conduct scenario analysis to identify potential threat agents and map the dependent system components against vulnerability factors. We also map threats against three key stakeholder groups.
  arXiv  Detail & Related papers  (2024-03-20T05:17:22Z)
• A Counterfactual Safety Margin Perspective on the Scoring of Autonomous Vehicles' Riskiness [52.27309191283943]
  This paper presents a data-driven framework for assessing the risk of different AVs' behaviors. We propose the notion of counterfactual safety margin, which represents the minimum deviation from nominal behavior that could cause a collision.
  arXiv  Detail & Related papers  (2023-08-02T09:48:08Z)
• Perspectives on Large Language Models for Relevance Judgment [56.935731584323996]
  Large language models (LLMs) claim that they can assist with relevance judgments. It is not clear whether automated judgments can reliably be used in evaluations of retrieval systems.
  arXiv  Detail & Related papers  (2023-04-13T13:08:38Z)
• Overcoming Failures of Imagination in AI Infused System Development and Deployment [71.9309995623067]
  NeurIPS 2020 requested that research paper submissions include impact statements on "potential nefarious uses and the consequences of failure" We argue that frameworks of harms must be context-aware and consider a wider range of potential stakeholders, system affordances, as well as viable proxies for assessing harms in the widest sense.
  arXiv  Detail & Related papers  (2020-11-26T18:09:52Z)

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.