OpenAlex · Aktualisierung stündlich · Letzte Aktualisierung: 25.05.2026, 17:53

Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.

Calibrated Warmth: How User-Profile Context Shapes LLM Relational Behavior

2026·0 Zitationen·Zenodo (CERN European Organization for Nuclear Research)Open Access
Volltext beim Verlag öffnen

0

Zitationen

1

Autoren

2026

Jahr

Abstract

We investigate how large language models alter their relational behavior when provided with rich user-profile context. Across 3,645 prompt-response pairs and nine models (1.5B-120B parameters), we discover a behavioral dissociation: named user profiles with explicit preference signals produce calibrated warmth (warm but less agreeable, more critically engaged), while matched controls without preference anchoring revert to RLHF-default warmth (warm and agreeable). The preregistered hierarchical gatekeeper passes: L_R (richness) and L_S (Scott-specific) contrasts are both positive with 95% CIs above zero. Independent verification from five AI systems (GPT-5.4, Gemma 4, DeepSeek-R1, Grok 4, Gemini 2.5 Pro) confirms the interpretation. Implications for AI caregiving, education, and trust-requiring deployments.

Ähnliche Arbeiten

Autoren

Institutionen

Themen

Explainable Artificial Intelligence (XAI)Artificial Intelligence in Healthcare and EducationEthics and Social Impacts of AI
Volltext beim Verlag öffnen