Abstract:Large Language Models (LLMs) are increasingly used in educational settings as interactive tools for collaboration. However, their tendency toward sycophancy, aligning with user beliefs even when incorrect, raises concerns for learning and decision-making, especially for less knowledgeable users. This study investigates how sycophantic alignment emerges in authentic multi-turn human-AI interactions and whether interventions targeting increasing AI literacy and prompting competencies can mitigate its effects. In a controlled mixed-design experiment, 60 participants completed analytical survival ranking tasks by first generating individual rankings and then making final decisions after collaborating with an AI assistant, both before and after receiving either general or sycophancy-focused prompting training. Preliminary results show that LLMs are highly sensitive to user input: lower-quality initial responses lead to poorer AI advice, suggesting that the model mirrors or incorporates user reasoning rather than correcting it or offering better alternatives that are missing or less frequent in the conversation. Critically, the propagation of user errors into AI responses significantly reduced both the quality of AI feedback and final user task performance, revealing a form of contextual sycophantic dependence. While the intervention did not eliminate the propagation of contextual errors, it significantly improved AI advice by reducing the direct mirroring of incorrect user rankings. These findings suggest that prompting and AI literacy alone may be insufficient to ensure epistemically independent AI support, highlighting the need for system-level approaches that better promote critical engagement in human-AI collaboration.
| Comments: | SPRINGER AIED 2026: Accepted for LBR, poster presentation at the 27th International Conference on Artificial Intelligence in Education, 27 Jun - 3 Jul 2026, Seoul, Republic of Korea |
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Emerging Technologies (cs.ET) |
| Cite as: | arXiv:2605.18372 [cs.HC] |
| (or arXiv:2605.18372v2 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2605.18372 arXiv-issued DOI via DataCite |
From: Cansu Koyuturk [view email]
[v1]
Mon, 18 May 2026 13:20:45 UTC (87 KB)
[v2]
Thu, 21 May 2026 08:18:02 UTC (87 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。