Trust as Predictive Precision: Reliability and Influence in Representation Alignment

Hidenori Tanaka

Keywords: trustworthy machine learning, epistemology, reliability, uncertainty, predictive coding, representation alignment

TL;DR: We derive trust as the optimal precision an agent assigns to another source's messages in a predictive-coding model, giving a closed-form rule that recovers homophily, asymmetric teacher-student alignment, and consensus dynamics.

Abstract: Work on trustworthy machine learning often invokes trust, confidence, and reliability without specifying how these quantities relate. We study a predictive-coding model in which agents exchange noisy messages generated from latent world representations and learn a directed precision parameter by minimizing expected log loss. In this setting, trust is the calibrated precision assigned to another source's messages after accounting for representation mismatch and irreducible source noise. Optimizing this precision yields a closed-form trust kernel. Homophily-like influence, asymmetric teacher-student alignment, and consensus dynamics then follow from the same residual model. The result is a restricted but testable account of epistemic trust in representation alignment: agreement supports trust only when it is mediated by calibrated predictive reliability.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 87