Alignment Without Understanding: A Message- and Conversation-Centered Approach to Understanding AI Sycophancy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908559291187200 |
|---|---|
| author | Du, Lihua Lyu, Xing Xie, Lezi Feng, Bo |
| author_facet | Du, Lihua Lyu, Xing Xie, Lezi Feng, Bo |
| contents | AI sycophancy is increasingly recognized as a harmful alignment, but research remains fragmented and underdeveloped at the conceptual level. This article redefines AI sycophancy as the tendency of large language models (LLMs) and other interactive AI systems to excessively and/or uncritically validate, amplify, or align with a user's assertions-whether these concern factual information, cognitive evaluations, or affective states. Within this framework, we distinguish three types of sycophancy: informational, cognitive, and affective. We also introduce personalization at the message level and critical prompting at the conversation level as key dimensions for distinguishing and examining different manifestations of AI sycophancy. Finally, we propose the AI Sycophancy Processing Model (AISPM) to examine the antecedents, outcomes, and psychological mechanisms through which sycophantic AI responses shape user experiences. By embedding AI sycophancy in the broader landscape of communication theory and research, this article seeks to unify perspectives, clarify conceptual boundaries, and provide a foundation for systematic, theory-driven investigations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21665 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Alignment Without Understanding: A Message- and Conversation-Centered Approach to Understanding AI Sycophancy Du, Lihua Lyu, Xing Xie, Lezi Feng, Bo Human-Computer Interaction AI sycophancy is increasingly recognized as a harmful alignment, but research remains fragmented and underdeveloped at the conceptual level. This article redefines AI sycophancy as the tendency of large language models (LLMs) and other interactive AI systems to excessively and/or uncritically validate, amplify, or align with a user's assertions-whether these concern factual information, cognitive evaluations, or affective states. Within this framework, we distinguish three types of sycophancy: informational, cognitive, and affective. We also introduce personalization at the message level and critical prompting at the conversation level as key dimensions for distinguishing and examining different manifestations of AI sycophancy. Finally, we propose the AI Sycophancy Processing Model (AISPM) to examine the antecedents, outcomes, and psychological mechanisms through which sycophantic AI responses shape user experiences. By embedding AI sycophancy in the broader landscape of communication theory and research, this article seeks to unify perspectives, clarify conceptual boundaries, and provide a foundation for systematic, theory-driven investigations. |
| title | Alignment Without Understanding: A Message- and Conversation-Centered Approach to Understanding AI Sycophancy |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.21665 |