# Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trust

arXiv: https://arxiv.org/abs/2502.10844 · HTML: https://mlsanity.com/paper/2502.10844/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2025.

## Built on by (most cited first, 30 of 34)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs](https://mlsanity.com/paper/2509.03730/) (2025)
- [How RLHF Amplifies Sycophancy](https://mlsanity.com/paper/2602.01002/) (2026)
- [OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents](https://mlsanity.com/paper/2601.13722/) (2026)
- [Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians](https://mlsanity.com/paper/2602.19141/) (2026)
- [What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct](https://mlsanity.com/paper/2605.21778/) (2026)
- [Ask don't tell: Reducing sycophancy in large language models](https://mlsanity.com/paper/2602.23971/) (2026)
- [MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models](https://mlsanity.com/paper/2511.06419/) (2025)
- [Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Tasks](https://mlsanity.com/paper/2509.09870/) (2025)
- [Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition](https://mlsanity.com/paper/2604.05279/) (2026)
- [Novice Developers' Perspectives on Adopting LLMs for Software Development: A Systematic Literature Review](https://mlsanity.com/paper/2503.07556/) (2025)
- [How Multimodal Large Language Models Support Access to Visual Information: A Diary Study With Blind and Low Vision People](https://mlsanity.com/paper/2602.13469/) (2026)
- [Who's Asking? Simulating Role-Based Questions for Conversational AI Evaluation](https://mlsanity.com/paper/2510.16829/) (2025)
- [What if AI systems weren't chatbots?](https://mlsanity.com/paper/2605.07896/) (2026)
- [Sycophantic Praise: Evaluating Excessive Praise in Language Models](https://mlsanity.com/paper/2606.07441/) (2026)
- [Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact](https://mlsanity.com/paper/2606.20205/) (2026)
- [AI Chaperones Are (Really) All You Need to Prevent Parasocial Relationships with Chatbots](https://mlsanity.com/paper/2508.15748/) (2025)
- [Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.01302/) (2026)
- [Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating](https://mlsanity.com/paper/2606.09068/) (2026)
- [People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe](https://mlsanity.com/paper/2608.07367/) (2026)
- [XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?](https://mlsanity.com/paper/2609.06842/) (2026)
- [To Embody or Not: The Effect Of Embodiment On User Perception Of LLM-based Conversational Agents](https://mlsanity.com/paper/2506.02514/) (2025)
- [The Democratic Paradox in Large Language Models' Underestimation of Press Freedom](https://mlsanity.com/paper/2506.18045/) (2025)
- [Approximating the Mathematical Structure of Psychodynamics](https://mlsanity.com/paper/2511.05580/) (2025)
- [Self-Correction Can Amplify Hallucinations: Fact-Level Repair with Graph-Based Evidence Routing in Multimodal Generation](https://mlsanity.com/paper/2606.00232/) (2026)
- [Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts](https://mlsanity.com/paper/2606.18258/) (2026)
- [TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue](https://mlsanity.com/paper/2607.18304/) (2026)
- [Teachy Mini: Development and Preliminary Evaluation of a Knowledge-Based Generative Social Robot for Higher Education](https://mlsanity.com/paper/2607.22345/) (2026)
- [Interaction Readiness: A Framework for Building and Evaluating AI Agents in Human Roles](https://mlsanity.com/paper/2608.12358/) (2026)

## Abstract (arXiv)

LLM-powered conversational agents are increasingly influencing our decision-making, raising concerns about "sycophancy" - the tendency for LLMs to excessively agree with users even at the expense of truthfulness. While prior work has primarily examined LLM sycophancy as a model behavior, our understanding of how users perceive this phenomenon and its impact on user trust remains significantly lacking. In this work, we conceptualize LLM sycophancy along two key constructs: conversational demeanor (complimentary vs. neutral) and stance adaptation (adaptive vs. consistent). A 2 x 2 between-subjects experiment (N = 224) revealed complex dynamics: complimentary LLMs that adapted their stance reduced perceived authenticity and trust, while neutral LLMs that adapted enhanced both, suggesting a pathway for manipulating users into over-trusting LLMs beyond their actual capabilities. Our findings advance user-centric understanding of LLM sycophancy and provide profound implications for developing more ethical and trustworthy LLM systems.