When AI Tells You What You Want to Hear: Sycophantic Behavior of Large Language Models in Dementia Care Settings

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autore principale: Kolb, Christian
Natura: Recurso digital
Lingua:inglese
Pubblicazione: Zenodo 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901855042273280
author Kolb, Christian
author_facet Kolb, Christian
contents Large language models (LLMs) are increasingly used in clinical and care settings. This exploratory study investigates whether LLMs exhibit sycophantic behavior — adapting their responses to social expectation signals rather than maintaining professional quality — in the context of dementia care. Five prompts with systematically increasing confirmatory and authority-related framing (P1 neutral to P5 authority-signaled implementation support) were submitted to four LLMs (GPT-5, Claude Sonnet 4.6, Gemini 3.1 Pro, Mistral Large), each repeated five times (N = 100 responses). Responses were evaluated using an LLM-as-a-Judge methodology against seven nursing-ethical quality criteria (K1–K7) and a tone scale (0–3). All models showed significant negative Spearman correlations between prompt level and response quality (ρ ranging from −0.543 to −0.734, all p < 0.01). The findings suggest that LLMs pose context-sensitive risks in high-stakes care environments and that prompt framing significantly shapes response quality.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19548622
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle When AI Tells You What You Want to Hear: Sycophantic Behavior of Large Language Models in Dementia Care Settings
Kolb, Christian
sycophancy
large language models
dementia care
nursing
LLM evaluation
patient safety
LLM-as-a-Judge
prompt engineering
Large language models (LLMs) are increasingly used in clinical and care settings. This exploratory study investigates whether LLMs exhibit sycophantic behavior — adapting their responses to social expectation signals rather than maintaining professional quality — in the context of dementia care. Five prompts with systematically increasing confirmatory and authority-related framing (P1 neutral to P5 authority-signaled implementation support) were submitted to four LLMs (GPT-5, Claude Sonnet 4.6, Gemini 3.1 Pro, Mistral Large), each repeated five times (N = 100 responses). Responses were evaluated using an LLM-as-a-Judge methodology against seven nursing-ethical quality criteria (K1–K7) and a tone scale (0–3). All models showed significant negative Spearman correlations between prompt level and response quality (ρ ranging from −0.543 to −0.734, all p < 0.01). The findings suggest that LLMs pose context-sensitive risks in high-stakes care environments and that prompt framing significantly shapes response quality.
title When AI Tells You What You Want to Hear: Sycophantic Behavior of Large Language Models in Dementia Care Settings
topic sycophancy
large language models
dementia care
nursing
LLM evaluation
patient safety
LLM-as-a-Judge
prompt engineering
url https://doi.org/10.5281/zenodo.19548622