Measuring What AI Systems Might Do: Towards A Measurement Science in AI

• URL: http://arxiv.org/abs/2603.00063v1
• Date: Tue, 10 Feb 2026 12:59:41 GMT
• Title: Measuring What AI Systems Might Do: Towards A Measurement Science in AI
• Abstract summary: capabilities, propensities, skills, values, and abilities are routinely used interchangeably and conflated with observable performance.<n>We argue that capabilities and propensities are dispositional properties - stable features of systems characterised by counterfactual relationships.
• Score: 19.687397197326817
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Scientists, policy-makers, business leaders, and members of the public care about what modern artificial intelligence systems are disposed to do. Yet terms such as capabilities, propensities, skills, values, and abilities are routinely used interchangeably and conflated with observable performance, with AI evaluation practices rarely specifying what quantity they purport to measure. We argue that capabilities and propensities are dispositional properties - stable features of systems characterised by counterfactual relationships between contextual conditions and behavioural outputs. Measuring a disposition requires (i) hypothesising which contextual properties are causally relevant, (ii) independently operationalising and measuring those properties, and (iii) empirically mapping how variation in those properties affects the probability of the behaviour. Dominant approaches to AI evaluation, from benchmark averages to data-driven latent-variable models such as Item Response Theory, bypass these steps entirely. Building on ideas from philosophy of science, measurement theory, and cognitive science, we develop a principled account of AI capabilities and propensities as dispositions, show why prevailing evaluation practices fail to measure them, and outline what disposition-respecting, scientifically defensible AI evaluation would require.

Related papers

• Multi-Dimensional Assessment for AI Cognition (MAAC): A Theoretical Framework for Process-Oriented Cognitive Evaluation of Text-Based AI Systems [1.8262547855491456]
  This paper introduces the Multi-Dimensional Assessment for AI Cognition (MAAC), a framework for shifting evaluation from what text-based AI systems produce to how they think.<n>MAAC defines nine cognitively motivated dimensions: Cognitive Load, Tool Execution, Content Quality, Memory Integration, Complexity Handling, Hallucination Control, Knowledge Transfer, Processing Efficiency, and Process-Outcome Alignment.<n>Five theoretical analyses provide initial support for the framework's coherence and empirical testability.
  arXiv  Detail & Related papers  (2026-08-01T14:01:17Z)
• Psychological Competence as a Missing Dimension in AI Evaluation [0.0]
  This paper introduces psychological competence as a missing dimension in AI evaluation.<n>We outline a conceptual framework for psychological competence and its core domains.<n>We argue that psychological competence should become a core consideration for model providers, deploying organizations, researchers, and regulators.
  arXiv  Detail & Related papers  (2026-07-09T09:29:01Z)
• What Does Your Benchmark Really Measure? A Framework for Robust Inference of AI Capabilities [0.773472615056109]
  Evaluations of generative models on benchmark data are now ubiquitous.<n>Yet growing skepticism surrounds their reliability.<n>How can we know that a reported accuracy genuinely reflects a model's true performance?<n>We make this step explicit by proposing a principled framework for evaluation as inference.
  arXiv  Detail & Related papers  (2025-09-23T21:29:04Z)
• 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)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)
• 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)
• Predictable Artificial Intelligence [77.1127726638209]
  This paper introduces the ideas and challenges of Predictable AI.<n>It explores the ways in which we can anticipate key validity indicators of present and future AI ecosystems.<n>We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI ecosystems.
  arXiv  Detail & Related papers  (2023-10-09T21:36:21Z)
• Position: AI Evaluation Should Learn from How We Test Humans [65.36614996495983]
  We argue that psychometrics, a theory originating in the 20th century for human assessment, could be a powerful solution to the challenges in today's AI evaluations.
  arXiv  Detail & Related papers  (2023-06-18T09:54:33Z)
• Evaluating Explainability in Machine Learning Predictions through Explainer-Agnostic Metrics [0.0]
  We develop six distinct model-agnostic metrics designed to quantify the extent to which model predictions can be explained. These metrics measure different aspects of model explainability, ranging from local importance, global importance, and surrogate predictions. We demonstrate the practical utility of these metrics on classification and regression tasks, and integrate these metrics into an existing Python package for public use.
  arXiv  Detail & Related papers  (2023-02-23T15:28:36Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)
• 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)
• The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies [1.2762298148425795]
  Lack of transparency is identified as one of the main barriers to implementation of AI systems in health care. We review the recent literature to provide guidance to researchers and practitioners on the design of explainable AI systems. We conclude that explainable modelling can contribute to trustworthy AI, but the benefits of explainability still need to be proven in practice.
  arXiv  Detail & Related papers  (2020-07-31T09:08:27Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)

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.