Predictable Artificial Intelligence

• URL: http://arxiv.org/abs/2310.06167v3
• Date: Tue, 07 Jan 2025 03:59:37 GMT
• Title: Predictable Artificial Intelligence
• Authors: Lexin Zhou, Pablo A. Moreno-Casares, Fernando Martínez-Plumed, John Burden, Ryan Burnell, Lucy Cheke, Cèsar Ferri, Alexandru Marcoci, Behzad Mehrbakhsh, Yael Moros-Daval, Seán Ó hÉigeartaigh, Danaja Rutar, Wout Schellaert, Konstantinos Voudouris, José Hernández-Orallo,
• Abstract summary: This paper introduces the ideas and challenges of Predictable AI. It explores the ways in which we can anticipate key validity indicators of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI ecosystems.
• Score: 77.1127726638209
• License:
• Abstract: We introduce the fundamental ideas and challenges of Predictable AI, a nascent research area that explores the ways in which we can anticipate key validity indicators (e.g., performance, safety) of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI ecosystems, and thus should be prioritised over performance. We formally characterise predictability, explore its most relevant components, illustrate what can be predicted, describe alternative candidates for predictors, as well as the trade-offs between maximising validity and predictability. To illustrate these concepts, we bring an array of illustrative examples covering diverse ecosystem configurations. Predictable AI is related to other areas of technical and non-technical AI research, but have distinctive questions, hypotheses, techniques and challenges. This paper aims to elucidate them, calls for identifying paths towards a landscape of predictably valid AI systems and outlines the potential impact of this emergent field.

Related papers

• Computational Safety for Generative AI: A Signal Processing Perspective [65.268245109828]
  computational safety is a mathematical framework that enables the quantitative assessment, formulation, and study of safety challenges in GenAI. We show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts. We discuss key open research challenges, opportunities, and the essential role of signal processing in computational AI safety.
  arXiv  Detail & Related papers  (2025-02-18T02:26:50Z)
• From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence [19.369216778200034]
  Uncertainty quantification (UQ) is a critical aspect of artificial intelligence (AI) systems. This review explores the evolution of uncertainty quantification techniques in AI. We examine the diverse applications of UQ across various fields, emphasizing its impact on decision-making, predictive accuracy, and system robustness.
  arXiv  Detail & Related papers  (2025-01-05T23:14:47Z)
• The Ethics of Advanced AI Assistants [53.89899371095332]
  This paper focuses on the opportunities and the ethical and societal risks posed by advanced AI assistants. We define advanced AI assistants as artificial agents with natural language interfaces, whose function is to plan and execute sequences of actions on behalf of a user. We consider the deployment of advanced assistants at a societal scale, focusing on cooperation, equity and access, misinformation, economic impact, the environment and how best to evaluate advanced AI assistants.
  arXiv  Detail & Related papers  (2024-04-24T23:18:46Z)
• A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI) [0.0]
  We argue that it is best approached in a nuanced way that incorporates resource availability, domain characteristics, and considerations of risk. This work aims to advance the field of Requirements Engineering for AI.
  arXiv  Detail & Related papers  (2023-07-26T15:15:44Z)
• What Should I Know? Using Meta-gradient Descent for Predictive Feature Discovery in a Single Stream of Experience [63.75363908696257]
  computational reinforcement learning seeks to construct an agent's perception of the world through predictions of future sensations. An open challenge in this line of work is determining from the infinitely many predictions that the agent could possibly make which predictions might best support decision-making. We introduce a meta-gradient descent process by which an agent learns what predictions to make, 2) the estimates for its chosen predictions, and 3) how to use those estimates to generate policies that maximize future reward.
  arXiv  Detail & Related papers  (2022-06-13T21:31:06Z)
• 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)
• Forecasting AI Progress: A Research Agenda [0.41998444721319206]
  This paper describes the development of a research agenda for forecasting AI progress. It uses the Delphi technique to elicit and aggregate experts' opinions on what questions and methods to prioritize. Experts indicated that a wide variety of methods should be considered for forecasting AI progress.
  arXiv  Detail & Related papers  (2020-08-04T21:46:46Z)
• AI Research Considerations for Human Existential Safety (ARCHES) [6.40842967242078]
  In negative terms, we ask what existential risks humanity might face from AI development in the next century. Key property of hypothetical AI technologies is introduced, called emphprepotence A set of auxrefdirtot contemporary research directions are then examined for their potential benefit to existential safety.
  arXiv  Detail & Related papers  (2020-05-30T02:05:16Z)

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.