Human Oversight-by-Design for Accessible Generative IUIs

TL;DR

This paper introduces a human oversight-by-design framework for accessible generative user interfaces, embedding human judgment and automated risk checks to ensure reliability, accessibility, and accountability in high-stakes AI-assisted workflows.

Contribution

It proposes an architectural approach integrating escalation policies, UI controls, and monitoring for scalable, verifiable human oversight in generative UI systems.

Findings

Automated risk checks improve detection of issues like hallucinations and bias.

Escalation policies ensure mandatory human review when risks are high.

Monitoring enables tuning of oversight policies over time.

Abstract

LLM-generated interfaces are increasingly used in high-consequence workflows (e.g., healthcare communication), where how information is presented can impact downstream actions. These interfaces and their content support human interaction with AI-assisted decision-making and communication processes and should remain accessible and usable for people with disabilities. Accessible plain-language interfaces serve as an enabling infrastructure for meaningful human oversight. In these contexts, ethical and trustworthiness risks, including hallucinations, semantic distortion, bias, and accessibility barriers, can undermine reliability and limit users' ability to understand, monitor, and intervene in AI-supported processes. Yet, in practice, oversight is often treated as a downstream check, without clear rules for when human intervention is required or who is accountable. We propose oversight-by-design: embedding human judgment across the pipeline as an architectural commitment, implemented via escalation policies and explicit UI controls for risk signalling and intervention. Automated checks flag risk in generated UI communication that supports high-stakes workflows (e.g., readability, semantic fidelity, factual consistency, and standards-based accessibility constraints) and escalate to mandatory Human-in-the-Loop (HITL) review before release when thresholds are violated, or uncertainty is high. Human-on-the-Loop (HOTL) supervision monitors system-level signals over time (alerts, escalation rates, and compliance evidence) to tune policies and detect drift. Structured review feedback is translated into governance actions (rule and prompt updates, threshold calibration, and traceable audit logs), enabling scalable intervention and verifiable oversight for generative UI systems that support high-stakes workflows.