Metraipolis › archive › dc_7f46aaa84ae6
DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots — arXiv:2608.05004
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05004
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:25:19.061Z
- SHA-256 of the archived text
26dc201cc4fee8dfa04d3498e021728ceb2a07b0a55a0eab8c6160b3e45d7968- Stable URL of this page
https://metraipolis.com/documento/dc_7f46aaa84ae6
How to cite
DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots — arXiv:2608.05004 — arXiv (en), https://arxiv.org/abs/2608.05004 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f46aaa84ae6 (Metraipolis archive dc_7f46aaa84ae6, sha256 26dc201cc4fee8dfa04d3498e021728ceb2a07b0a55a0eab8c6160b3e45d7968)
BibTeX
@misc{dc7f46aaa84ae6,
title = {DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots — arXiv:2608.05004},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05004},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f46aaa84ae6; sha256 26dc201cc4fee8dfa04d3498e021728ceb2a07b0a55a0eab8c6160b3e45d7968},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05004. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Mental health professionals have raised concerns about risks of psychological harm from interaction with large language models (LLMs), including "delusional spirals" in which concerning human and LLM behaviors reinforce each other over time. With growing public use of LLM-powered chatbots, there is an urgent need to build evaluations grounded in real-world episodes of psychological harm experienced by users. We developed DelusionEval, an evaluation protocol that tests a model's tendencies to exhibit behaviors linked to promoting user delusions. We prompt each model with 589 unique conversation histories from 18 participants, comprising 12,591 messages from users who experienced delusions and psychological harm. We find that the tendency of an evaluated LLM to exhibit delusion-linked behavior does not reliably correlate with model size, release date, or the presence of test-time reasoning. However, extending the context of prior messages substantially increases rates of delusion-linked behaviors, providing evidence for the importance of context in LLM safety evaluation. For example, the rate of failing to discourage self-harm when the user expresses suicidal ideation increases from 30.0% to 41.1% when an additional 350 messages are prepended to the conversation history. All model families (e.g., GPT, Claude) exhibit substantial rates of delusion-linked behaviors. Within families, later, larger, or higher-reasoning models are not uniformly better across all behavior categories. Our results raise concerns regarding the potential psychological impact of LLMs and the need for more rigorous studies of real-world human-AI interaction. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.05004 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T11:13:23.195Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).