A Conceptual Framework for AI Capability Evaluations

• URL: http://arxiv.org/abs/2506.18213v1
• Date: Mon, 23 Jun 2025 00:19:27 GMT
• Title: A Conceptual Framework for AI Capability Evaluations
• Authors: María Victoria Carro, Denise Alejandra Mester, Francisca Gauna Selasco, Luca Nicolás Forziati Gangi, Matheo Sandleris Musa, Lola Ramos Pereyra, Mario Leiva, Juan Gustavo Corvalan, María Vanina Martinez, Gerardo Simari,
• Abstract summary: We propose a conceptual framework for analyzing AI capability evaluations.<n>It offers a structured, descriptive approach that systematizes the analysis of widely used methods and terminology.<n>It also enables researchers to identify methodological weaknesses, assists practitioners in designing evaluations, and provides policymakers with a tool to scrutinize, compare, and navigate complex evaluation landscapes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence about system capabilities and risks. Yet there remains a lack of clarity on how to perform these assessments both comprehensively and reliably. To address this gap, we propose a conceptual framework for analyzing AI capability evaluations, offering a structured, descriptive approach that systematizes the analysis of widely used methods and terminology without imposing new taxonomies or rigid formats. This framework supports transparency, comparability, and interpretability across diverse evaluations. It also enables researchers to identify methodological weaknesses, assists practitioners in designing evaluations, and provides policymakers with an accessible tool to scrutinize, compare, and navigate complex evaluation landscapes.

Related papers

• Developing and Maintaining an Open-Source Repository of AI Evaluations: Challenges and Insights [44.99833362998488]
  This paper presents practical insights from eight months of maintaining $_evals$, an open-source repository of 70+ community-contributed AI evaluations.<n>We identify key challenges in implementing and maintaining AI evaluations and develop solutions.
  arXiv  Detail & Related papers  (2025-07-09T14:30:45Z)
• A Systematic Review of User-Centred Evaluation of Explainable AI in Healthcare [1.57531613028502]
  This study aims to develop a framework of well-defined, atomic properties that characterise the user experience of XAI in healthcare.<n>We also provide context-sensitive guidelines for defining evaluation strategies based on system characteristics.
  arXiv  Detail & Related papers  (2025-06-16T18:30:00Z)
• Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods [0.0]
  This literature review consolidates the rapidly evolving field of AI safety evaluations.<n>It proposes a systematic taxonomy around three dimensions: what properties we measure, how we measure them, and how these measurements integrate into frameworks.
  arXiv  Detail & Related papers  (2025-05-08T16:55:07Z)
• Securing External Deeper-than-black-box GPAI Evaluations [49.1574468325115]
  This paper examines the critical challenges and potential solutions for conducting secure and effective external evaluations of general-purpose AI (GPAI) models.<n>With the exponential growth in size, capability, reach and accompanying risk, ensuring accountability, safety, and public trust requires frameworks that go beyond traditional black-box methods.
  arXiv  Detail & Related papers  (2025-03-10T16:13:45Z)
• Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework [61.38174427966444]
  Large Language Models (LLMs) are being used more and more extensively for automated evaluation in various scenarios.<n>Previous studies have attempted to fine-tune open-source LLMs to replicate the evaluation explanations and judgments of powerful proprietary models.<n>We propose a novel evaluation framework, ARJudge, that adaptively formulates evaluation criteria and synthesizes both text-based and code-driven analyses.
  arXiv  Detail & Related papers  (2025-02-26T06:31:45Z)
• A Unified Framework for Evaluating the Effectiveness and Enhancing the Transparency of Explainable AI Methods in Real-World Applications [2.0681376988193843]
  "Black box" characteristic of AI models constrains interpretability, transparency, and reliability.<n>This study presents a unified XAI evaluation framework to evaluate correctness, interpretability, robustness, fairness, and completeness of explanations generated by AI models.
  arXiv  Detail & Related papers  (2024-12-05T05:30:10Z)
• Pessimistic Evaluation [58.736490198613154]
  We argue that evaluating information access systems assumes utilitarian values not aligned with traditions of information access based on equal access. We advocate for pessimistic evaluation of information access systems focusing on worst case utility.
  arXiv  Detail & Related papers  (2024-10-17T15:40:09Z)
• What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks [16.795332276080888]
  We propose a fine-grained validation framework for explainable artificial intelligence systems. We recognise their inherent modular structure: technical building blocks, user-facing explanatory artefacts and social communication protocols.
  arXiv  Detail & Related papers  (2024-03-19T13:45:34Z)
• Evaluating General-Purpose AI with Psychometrics [43.85432514910491]
  We discuss the need for a comprehensive and accurate evaluation of general-purpose AI systems such as large language models. Current evaluation methodology, mostly based on benchmarks of specific tasks, falls short of adequately assessing these versatile AI systems. To tackle these challenges, we suggest transitioning from task-oriented evaluation to construct-oriented evaluation.
  arXiv  Detail & Related papers  (2023-10-25T05:38:38Z)
• Towards a Comprehensive Human-Centred Evaluation Framework for Explainable AI [1.7222662622390634]
  We propose to adapt the User-Centric Evaluation Framework used in recommender systems. We integrate explanation aspects, summarise explanation properties, indicate relations between them, and categorise metrics that measure these properties.
  arXiv  Detail & Related papers  (2023-07-31T09:20:16Z)
• Modelling Assessment Rubrics through Bayesian Networks: a Pragmatic Approach [40.06500618820166]
  This paper presents an approach to deriving a learner model directly from an assessment rubric. We illustrate how the approach can be applied to automatize the human assessment of an activity developed for testing computational thinking skills.
  arXiv  Detail & Related papers  (2022-09-07T10:09:12Z)
• An interdisciplinary conceptual study of Artificial Intelligence (AI) for helping benefit-risk assessment practices: Towards a comprehensive qualification matrix of AI programs and devices (pre-print 2020) [55.41644538483948]
  This paper proposes a comprehensive analysis of existing concepts coming from different disciplines tackling the notion of intelligence. The aim is to identify shared notions or discrepancies to consider for qualifying AI systems.
  arXiv  Detail & Related papers  (2021-05-07T12:01:31Z)
• Multisource AI Scorecard Table for System Evaluation [3.74397577716445]
  The paper describes a Multisource AI Scorecard Table (MAST) that provides the developer and user of an artificial intelligence (AI)/machine learning (ML) system with a standard checklist. The paper explores how the analytic tradecraft standards outlined in Intelligence Community Directive (ICD) 203 can provide a framework for assessing the performance of an AI system.
  arXiv  Detail & Related papers  (2021-02-08T03:37:40Z)

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.