The Trust Calibration Maturity Model for Characterizing and Communicating Trustworthiness of AI Systems

2025-01-28

arXiv.org

AI Summary

Amid growing concerns over insufficient evaluation metrics for AI system trustworthiness and difficulties in calibrating user trust in the large language model era, this paper proposes the Trustworthiness Calibration Maturity Model (TCMM)—the first multidimensional maturity framework explicitly designed for user trust calibration. TCMM establishes a structured, measurable, communicable, and evolvable metric system across five dimensions: performance characterization, bias and robustness, transparency, safety and security, and usability—thereby enabling systematic quantification and articulation of abstract trustworthiness. Through maturity modeling, multidimensional trust assessment, and governance framework design, TCMM delivers theoretical formalization and standardized definitions. Empirical validation on two AI system–task pairs demonstrates its practical efficacy, significantly improving users’ accuracy in perceiving AI capability boundaries and enhancing usage rationality.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: User Experience and Usability

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The proliferation of powerful AI capabilities and systems necessitates a commensurate focus on user trust. We introduce the Trust Calibration Maturity Model (TCMM) to capture and communicate the maturity of AI system trustworthiness. The TCMM scores maturity along 5 dimensions that drive user trust: Performance Characterization, Bias&Robustness Quantification, Transparency, Safety&Security, and Usability. Information captured in the TCMM can be presented along with system performance information to help a user to appropriately calibrate trust, to compare requirements with current states of development, and to clarify trustworthiness needs. We present the TCMM and demonstrate its use on two AI system-target task pairs.

Problem

• Characterizing trustworthiness of AI systems for user calibration
• Addressing inaccessibility of trust evaluation in large-scale AI
• Providing a maturity model to assess AI trust dimensions

Innovation

• Proposes Trust Calibration Maturity Model (TCMM)
• Incorporates five dimensions of analytic maturity
• Demonstrates TCMM on ChatGPT and PhaseNet