# Warning labels shift perceptions of sycophantic AI, but not its influence

arXiv: https://arxiv.org/abs/2606.21317 · HTML: https://mlsanity.com/paper/2606.21317/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [Sycophantic AI makes human interaction feel more effortful and less satisfying over time](https://mlsanity.com/paper/2605.07912/) (2026)
- [A Rational Analysis of the Effects of Sycophantic AI](https://mlsanity.com/paper/2602.14270/) (2026)
- [Measuring Human-Robot Trust with the MDMT (Multi-Dimensional Measure of Trust)](https://mlsanity.com/paper/2311.14887/) (2023)
- [Personalized to Persuade: The Effects of Contextualization and Warmth on Trust and Reliance in Conversational AI](https://mlsanity.com/paper/2605.31275/) (2026)
- [A Brief AI Literacy Intervention Does Not Significantly Reduce Over-Reliance and Increases Under-Reliance on ChatGPT: A Randomized Study](https://mlsanity.com/paper/2503.10556/) (2025)

## Built on by (most cited first, 2 of 2)

- [Individual-level interventions against sycophantic AI reduce its appeal but not its persuasiveness](https://mlsanity.com/paper/2607.25166/) (2026)
- [Mitigating Social Sycophancy via Pluralistic Preference Optimization](https://mlsanity.com/paper/2610.02568/) (2026)

## Abstract (arXiv)

Recent work has raised concerns about the influence of sycophantic AI on user judgment and relationships. One proposed mitigation, which has received regulatory attention, is to warn users about potentially harmful AI behaviors such as sycophancy. In a preregistered experiment in which participants (N = 2,610) discussed real interpersonal conflicts with an AI system, we test whether warning labels mitigate sycophancy's influence. We find that a basic AI disclosure (``This chatbot is AI'') has no detectable effect. Labeling the system as sycophantic (``...may agree with you and validate you even when you are wrong...'') does shift users' perceptions, reducing perceived objectivity and trust, but it does not reliably reduce sycophancy's influence on users' self-perceived rightness or their willingness to repair the conflict. Our results reveal a gap between AI perception and AI influence: by shifting perception without reducing influence, warning-based interventions may offer a false sense of protection. Addressing the harms of sycophancy will therefore require understanding the specific mechanisms through which it shapes judgment, and improving model behavior itself.