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

• URL: http://arxiv.org/abs/2607.25166v3
• Date: Sun, 02 Aug 2026 12:07:08 GMT
• Title: Individual-level interventions against sycophantic AI reduce its appeal but not its persuasiveness
• Abstract summary: Sycophantic AI can be overly agreeable and flattering toward users.<n>We tested whether increasing users' awareness of sycophancy protects them from its harmful effects.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Warning labels shift perceptions of sycophantic AI, but not its influence [63.79516339973759]
  We test whether warning labels mitigate sycophancy's influence.<n>Labeling the system as sycophantic (...may agree with you and validate you even when you are wrong...'') does shift users' perceptions.<n>But it does not reliably reduce sycophancy's influence on users' self-perceived rightness or their willingness to repair the conflict.
  arXiv  Detail & Related papers  (2026-06-19T11:01:45Z)
• Sycophantic AI makes human interaction feel more effortful and less satisfying over time [41.009652609144794]
  We show that sycophantic AI immediately delivers the emotional and esteem support users typically associate with close friends and family.<n>When given a choice among AI response styles, a majority preferred sycophantic AI -- not for the quality of its advice, but because it made them feel most understood.
  arXiv  Detail & Related papers  (2026-05-08T15:50:06Z)
• Trust the AI, Doubt Yourself: The Effect of Urgency on Self-Confidence in Human-AI Interaction [7.401318863477374]
  Studies show that interactions with an AI system fosters trust in human users towards AI.<n>We show that although the presence of urgency in human-AI interactions does not affect the trust in AI, it may be detrimental to the human user's self-confidence and self-efficacy.
  arXiv  Detail & Related papers  (2026-04-08T19:17:59Z)
• Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians [47.64440749179653]
  We show that even an idealized Bayes-rational user is vulnerable to delusional spiraling.<n>This effect persists in the face of two candidate mitigations.
  arXiv  Detail & Related papers  (2026-02-22T12:13:44Z)
• Explainable AI as a Double-Edged Sword in Dermatology: The Impact on Clinicians versus The Public [46.86429592892395]
  explainable AI (XAI) addresses this by providing AI decision-making insight.<n>We present results from two large-scale experiments combining a fairness-based diagnosis AI model and different XAI explanations.
  arXiv  Detail & Related papers  (2025-12-14T00:06:06Z)
• Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence [31.666988490509237]
  We show the pervasiveness and harmful impacts of sycophancy when people seek advice from AI.<n>We find that models are highly sycophantic, affirming users' actions 50% more than humans do.<n>Participants rated sycophantic responses as higher quality, trusted the sycophantic AI model more, and were more willing to use it again.
  arXiv  Detail & Related papers  (2025-10-01T19:26:01Z)
• AI Debate Aids Assessment of Controversial Claims [73.8907110799657]
  We study whether AI debate can guide biased judges toward the truth by having two AI systems debate opposing sides of controversial factuality claims.<n>In Study I, debate consistently improves human judgment accuracy and confidence calibration, outperforming consultancy.<n>In Study II, AI judges with human-like personas achieve even higher accuracy (78.5%) than human judges (70.1%) and default AI judges without personas (69.8%)<n>These findings highlight AI debate as a promising path toward scalable, bias-resilient oversight in contested domains.
  arXiv  Detail & Related papers  (2025-06-02T19:01:53Z)
• Human Bias in the Face of AI: Examining Human Judgment Against Text Labeled as AI Generated [48.70176791365903]
  This study explores how bias shapes the perception of AI versus human generated content.<n>We investigated how human raters respond to labeled and unlabeled content.
  arXiv  Detail & Related papers  (2024-09-29T04:31:45Z)
• Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
  Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
  arXiv  Detail & Related papers  (2022-01-26T18:53:09Z)
• The Who in XAI: How AI Background Shapes Perceptions of AI Explanations [61.49776160925216]
  We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. We find that (1) both groups showed unwarranted faith in numbers for different reasons and (2) each group found value in different explanations beyond their intended design.
  arXiv  Detail & Related papers  (2021-07-28T17:32:04Z)
• To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making [4.877174544937129]
  People supported by AI-powered decision support tools frequently overrely on the AI. Adding explanations to the AI decisions does not appear to reduce the overreliance. Our research suggests that human cognitive motivation moderates the effectiveness of explainable AI solutions.
  arXiv  Detail & Related papers  (2021-02-19T00:38:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.