Assessing Human Rights Risks in AI: A Framework for Model Evaluation

• URL: http://arxiv.org/abs/2510.05519v1
• Date: Tue, 07 Oct 2025 02:12:56 GMT
• Title: Assessing Human Rights Risks in AI: A Framework for Model Evaluation
• Authors: Vyoma Raman, Camille Chabot, Betsy Popken,
• Abstract summary: We contribute to the field of algorithmic auditing by presenting a framework to computationally assess human rights risk.<n>We develop an approach to evaluating a model to make grounded claims about the level of risk a model poses to particular human rights.<n>Because a human rights approach centers on real-world harms, it requires evaluating AI systems in the specific contexts in which they are deployed.
• Score: 0.10195618602298682
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Universal Declaration of Human Rights and other international agreements outline numerous inalienable rights that apply across geopolitical boundaries. As generative AI becomes increasingly prevalent, it poses risks to human rights such as non-discrimination, health, and security, which are also central concerns for AI researchers focused on fairness and safety. We contribute to the field of algorithmic auditing by presenting a framework to computationally assess human rights risk. Drawing on the UN Guiding Principles on Business and Human Rights, we develop an approach to evaluating a model to make grounded claims about the level of risk a model poses to particular human rights. Our framework consists of three parts: selecting tasks that are likely to pose human rights risks within a given context, designing metrics to measure the scope, scale, and likelihood of potential risks from that task, and analyzing rights with respect to the values of those metrics. Because a human rights approach centers on real-world harms, it requires evaluating AI systems in the specific contexts in which they are deployed. We present a case study of large language models in political news journalism, demonstrating how our framework helps to design an evaluation and benchmarking different models. We then discuss the implications of the results for the rights of access to information and freedom of thought and broader considerations for adopting this approach.

Related papers

• When Do Language Models Endorse Limitations on Human Rights Principles? [82.84306700922664]
  We evaluate how Large Language Models (LLMs) navigate trade-offs involving the Universal Declaration of Human Rights (UDHR)<n>Our analysis of eleven major LLMs reveals systematic biases where models accept limiting Economic, Social, and Cultural rights more often than Political and Civil rights.
  arXiv  Detail & Related papers  (2026-03-04T16:01:53Z)
• 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)
• A Study on the Framework for Evaluating the Ethics and Trustworthiness of Generative AI [6.664765506069473]
  generative AI, such as ChatGPT, demonstrates remarkable innovative potential.<n>It simultaneously raises ethical and social concerns, including bias, harmfulness, copyright infringement, privacy violations, and hallucination.<n>This study emphasizes the need for new human_centered criteria that also reflect social impact.
  arXiv  Detail & Related papers  (2025-08-30T07:38:07Z)
• Foundations for Risk Assessment of AI in Protecting Fundamental Rights [0.5093073566064981]
  This chapter introduces a conceptual framework for qualitative risk assessment of AI.<n>It addresses the complexities of legal compliance and fundamental rights protection by itegrating definitional balancing and defeasible reasoning.
  arXiv  Detail & Related papers  (2025-07-24T10:52:22Z)
• AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons [62.374792825813394]
  This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability.<n>The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories.
  arXiv  Detail & Related papers  (2025-02-19T05:58:52Z)
• The Fundamental Rights Impact Assessment (FRIA) in the AI Act: Roots, legal obligations and key elements for a model template [55.2480439325792]
  Article aims to fill existing gaps in the theoretical and methodological elaboration of the Fundamental Rights Impact Assessment (FRIA)<n>This article outlines the main building blocks of a model template for the FRIA.<n>It can serve as a blueprint for other national and international regulatory initiatives to ensure that AI is fully consistent with human rights.
  arXiv  Detail & Related papers  (2024-11-07T11:55:55Z)
• An evidence-based methodology for human rights impact assessment (HRIA) in the development of AI data-intensive systems [49.1574468325115]
  We show that human rights already underpin the decisions in the field of data use. This work presents a methodology and a model for a Human Rights Impact Assessment (HRIA) The proposed methodology is tested in concrete case-studies to prove its feasibility and effectiveness.
  arXiv  Detail & Related papers  (2024-07-30T16:27:52Z)
• CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility [62.74405775089802]
  We present CValues, the first Chinese human values evaluation benchmark to measure the alignment ability of LLMs. As a result, we have manually collected adversarial safety prompts across 10 scenarios and induced responsibility prompts from 8 domains. Our findings suggest that while most Chinese LLMs perform well in terms of safety, there is considerable room for improvement in terms of responsibility.
  arXiv  Detail & Related papers  (2023-07-19T01:22:40Z)
• A Human Rights-Based Approach to Responsible AI [11.823731447853252]
  We argue that a human rights framework orients the research in this space away from the machines and the risks of their biases, and towards humans and the risks to their rights.
  arXiv  Detail & Related papers  (2022-10-06T04:07:53Z)
• Achieving a Data-driven Risk Assessment Methodology for Ethical AI [3.523208537466128]
  We show that a multidisciplinary research approach is the foundation of a pragmatic definition of ethical and societal risks faced by organizations using AI. We propose a novel data-driven risk assessment methodology, entitled DRESS-eAI.
  arXiv  Detail & Related papers  (2021-11-29T12:55:33Z)

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.