Abstract

USCH addresses a problem that output-level hallucination does not fully capture. In sustained AI dialogue, users can gradually develop contextual hallucinations that influence cognition, belief, trust, behavior, and self-understanding even when the model is operating within technical specification.

Paper Scope

The paper distinguishes model hallucination from user-side contextual hallucination, frames USCH as a non-clinical construct, and proposes a three-layer context model, a six-stage formation process, and fourteen observable phenomena.

Preview of the first page of the USCH paper

Embedded PDF viewing is unavailable in this browser. Use the open or download actions above to read the full paper.

This page embeds the paper PDF for online reading. If the built-in viewer is unavailable in your browser, use the open or download actions above.