Buchumschlag

Alignment Without Understanding: A Message- and Conversation-Centered Approach to Understanding AI Sycophancy

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Du, Lihua, Lyu, Xing, Xie, Lezi, Feng, Bo
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Human-Computer Interaction
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

The Fragility of AI Companionship: Ontological, Structural, and Normative Uncertainty in Human-AI Relationships
von: Zhang, Renwen, et al.
Veröffentlicht: (2026)

Conversational Self-Play for Discovering and Understanding Psychotherapy Approaches
von: Kampman, Onno P, et al.
Veröffentlicht: (2025)

Making Sense of Scams: Understanding Scam Conversations Through Multi-Level Alignment
von: Mao, Zhenyu, et al.
Veröffentlicht: (2026)

Controlling AI Agent Participation in Group Conversations: A Human-Centered Approach
von: Houde, Stephanie, et al.
Veröffentlicht: (2025)

Adapting AI to the Moment: Understanding the Dynamics of Parent-AI Collaboration Modes in Real-Time Conversations with Children
von: Mei, Yu, et al.
Veröffentlicht: (2026)

Signaling Human Intentions to Service Robots: Understanding the Use of Social Cues during In-Person Conversations
von: Lyu, Hanfang, et al.
Veröffentlicht: (2025)

"What If My Face Gets Scanned Without Consent": Understanding Older Adults' Experiences with Biometric Payment
von: Deng, Yue, et al.
Veröffentlicht: (2026)

Interaction Context Often Increases Sycophancy in LLMs
von: Jain, Shomik, et al.
Veröffentlicht: (2025)

The Illusion of Agreement with ChatGPT: Sycophancy and Beyond
von: Noshin, Kazi, et al.
Veröffentlicht: (2026)

The Social Sycophancy Scale: A psychometrically validated measure of sycophancy
von: Rehani, Jean, et al.
Veröffentlicht: (2026)

User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions
von: Fan, Xianzhe, et al.
Veröffentlicht: (2024)

Understanding Design Fixation in Generative AI
von: Chen, Liuqing, et al.
Veröffentlicht: (2025)

Explanations as Dialogues: Toward Human-Centered Conversational Explainable AI
von: Mathur, Niharika, et al.
Veröffentlicht: (2026)

Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks
von: Kasneci, Enkelejda, et al.
Veröffentlicht: (2026)

A Survey of LLM Alignment: Instruction Understanding, Intention Reasoning, and Reliable Generation
von: Chang, Zongyu, et al.
Veröffentlicht: (2025)

Understanding Codebase like a Professional! Human-AI Collaboration for Code Comprehension
von: Gao, Jie, et al.
Veröffentlicht: (2025)

Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents
von: Sharma, Nikhil, et al.
Veröffentlicht: (2026)

Designing for Being-With: Presence Without Personhood in Conversational Human-AI Interaction
von: Fried, Hector Michael, et al.
Veröffentlicht: (2026)

Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trust
von: Sun, Yuan, et al.
Veröffentlicht: (2025)

"It feels like hard work trying to talk to it": Understanding Older Adults' Experiences of Encountering and Repairing Conversational Breakdowns with AI Systems
von: Mathur, Niharika, et al.
Veröffentlicht: (2025)

Incremental XAI: Memorable Understanding of AI with Incremental Explanations
von: Bo, Jessica Y., et al.
Veröffentlicht: (2024)

From Data to Actionable Understanding: A Learner-Centered Framework for Dynamic Learning Analytics
von: Sadallah, Madjid
Veröffentlicht: (2025)

Understanding Communication Preferences of Information Workers in Engagement with Text-Based Conversational Agents
von: Bhattacharjee, Ananya, et al.
Veröffentlicht: (2024)

Towards Social AI: A Survey on Understanding Social Interactions
von: Lee, Sangmin, et al.
Veröffentlicht: (2024)

Sometimes You Need Facts, and Sometimes a Hug: Understanding Older Adults' Preferences for Explanations in LLM-Based Conversational AI Systems
von: Mathur, Niharika, et al.
Veröffentlicht: (2025)

Ground-Truth Depth in Vision Language Models: Spatial Context Understanding in Conversational AI for XR-Robotic Support in Emergency First Response
von: Maquilon, Rodrigo Gutierrez, et al.
Veröffentlicht: (2026)

Editrail: Understanding AI Usage by Visualizing Student-AI Interaction in Code
von: Zhang, Ashley Ge, et al.
Veröffentlicht: (2026)

PACEE: Parent-Centered AI Scaffolding for Emotion Education in Early Childhood Conversations
von: Mei, Yu, et al.
Veröffentlicht: (2025)

Understanding Password Preferences, Memorability, and Security through a Human-Centered Lens
von: Paker, Duru, et al.
Veröffentlicht: (2026)

AI Phenomenology for Understanding Human-AI Experiences Across Eras
von: Yun, Bhada, et al.
Veröffentlicht: (2026)

Understanding How Psychological Distance Influences User Preferences in Conversational Versus Web Search
von: Yang, Yitian, et al.
Veröffentlicht: (2024)

Understanding the Practices, Perceptions, and (Dis)Trust of Generative AI among Instructors: A Mixed-methods Study in the U.S. Higher Education
von: Lyu, Wenhan, et al.
Veröffentlicht: (2025)

Ironies of Generative AI: Understanding and mitigating productivity loss in human-AI interactions
von: Simkute, Auste, et al.
Veröffentlicht: (2024)

Understanding the Effects of AI-Assisted Critical Thinking on Human-AI Decision Making
von: Tian, Harry Yizhou, et al.
Veröffentlicht: (2026)

Co-Constructing Alignment: A Participatory Approach to Situate AI Values
von: Arzberger, Anne, et al.
Veröffentlicht: (2026)

Understanding How International Students in the U.S. Are Using Conversational AI to Support Cross-Cultural Adaptation
von: Nourian, Laleh, et al.
Veröffentlicht: (2026)

ScamGPT-J: Inside the Scammer's Mind, A Generative AI-Based Approach Toward Combating Messaging Scams
von: Tan, Xue Wen, et al.
Veröffentlicht: (2024)

Understanding Reader Perception Shifts upon Disclosure of AI Authorship
von: Nakano, Hiroki, et al.
Veröffentlicht: (2025)

Understanding and Shaping Human-Technology Assemblages in the Age of Generative AI
von: Andres, Josh, et al.
Veröffentlicht: (2024)

Understanding Data Understanding: A Framework to Navigate the Intricacies of Data Analytics
von: Holstein, Joshua, et al.
Veröffentlicht: (2024)