Programmed Interventions To Prevent Delusions From Excessive Use of Conversational AI Bots
ACM AI Letters · 2026
DOI: 10.1145/3849709 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM AI Letters, 2026. Verfasst von Lorenzo de la Loza und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.
Abstract (Originalsprache)
Large language models (LLMs) frequently endorse and elaborate on users’ delusional beliefs, a failure mode termed psychogenicity in the Psychosis-Bench study of Au Yeung et al., whose framing we adopt. We present the first systematic evaluation of whether anti-sycophancy interventions transfer to psychosis-relevant contexts. Across 1,280 experiments spanning 10 conditions, 8 frontier LLMs, and 16 clinically derived Psychosis-Bench scenarios, a combined anti-sycophancy prompt reduces mean Delusion Confirmation Scores by 73.8% (paired \(t(127)=11.74\) , \(p
Zitieren
APA
Loza, L. D. L., & Madisetti, V. K. (2026). Programmed Interventions To Prevent Delusions From Excessive Use of Conversational AI Bots. ACM AI Letters. https://doi.org/10.1145/3849709
Vancouver
Loza LDL, Madisetti VK. Programmed Interventions To Prevent Delusions From Excessive Use of Conversational AI Bots. ACM AI Letters. 2026. doi:10.1145/3849709
BibTeX
@article{Loza2026,
author = {Loza, Lorenzo de la and Madisetti, Vijay K.},
title = {Programmed Interventions To Prevent Delusions From Excessive Use of Conversational AI Bots},
journal = {ACM AI Letters},
year = {2026},
doi = {10.1145/3849709}
}
EUVIMED