When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
cs.AI
Submitted: 2026-05-06
Updated: 2026-11-06
Terminology
Sources
- To Agree or To Be Right? The Grounding-Sycophancy Tradeoff in Medical Vision-Language Models
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- A Rational Analysis of the Effects of Sycophantic AI
- On the Opportunities and Risks of Foundation Models
- Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
- Alignment Without Understanding: A Message- and Conversation-Centered Approach to Understanding AI Sycophancy
- AI generates well-liked but templatic empathic responses
- Practicing with Language Models Cultivates Human Empathic Communication
- LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
- TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models
- User Detection and Response Patterns of Sycophantic Behavior in Conversational AI
- Moral Sycophancy in Vision Language Models
- PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models
- When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour
- The Social Sycophancy Scale: A psychometrically validated measure of sycophancy
- From Sycophancy to Deception: A Unified Taxonomy for LLM Spontaneous Misalignment
- LLM-based Cognitive Models of Students with Misconceptions
- Heartificial Intelligence: Exploring Empathy in Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents