# Individual-level interventions against sycophantic AI reduce its appeal but not its persuasiveness

arXiv: https://arxiv.org/abs/2607.25166 · HTML: https://mlsanity.com/paper/2607.25166/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial](https://mlsanity.com/paper/2403.14380/) (2024)
- [What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct](https://mlsanity.com/paper/2605.21778/) (2026)
- [Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks](https://mlsanity.com/paper/2510.03667/) (2025)
- [AI systems out-persuade expert humans](https://mlsanity.com/paper/2606.16475/) (2026)
- [Measuring Human-Robot Trust with the MDMT (Multi-Dimensional Measure of Trust)](https://mlsanity.com/paper/2311.14887/) (2023)
- [Warning labels shift perceptions of sycophantic AI, but not its influence](https://mlsanity.com/paper/2606.21317/) (2026)

## Built on by (most cited first, 1 of 1)

- [Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness](https://mlsanity.com/paper/2609.26865/) (2026)

## Abstract (arXiv)

AI chatbots can be "sycophantic," or overly agreeable and flattering toward users. Sycophantic AI has been shown to entrench attitudes, yet users frequently fail to recognize it (a phenomenon we call "sycophancy blindness"). We tested whether increasing users' awareness of sycophancy protects them from its harmful effects in two preregistered experiments (n = 1,590). In the first, participants received a brief written warning about sycophancy before conversing with a sycophantic chatbot. In the second, participants watched a video of a sycophantic AI validating several other users, including users on opposite sides of the same conflict, before interacting with it themselves. Both interventions changed how participants evaluated the AI. The warning reduced the AI's perceived objectivity, and the video reduced enjoyment of the AI --- an effect mediated by the reduced belief that its validation was uniquely earned. We then pooled our experiments with two prior studies of sycophancy awareness interventions (six interventions total, n = 3,982). The pattern across experiments was consistent: while the interventions made the sycophantic AI appear less objective and trustworthy, none reduced its persuasiveness. These results suggest that individual-level interventions, such as warning labels or AI literacy, may not be enough to protect users from AI harms.