# The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration

arXiv: https://arxiv.org/abs/2605.18372 · HTML: https://mlsanity.com/paper/2605.18372/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 14 of 14)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [A Theoretical Analysis of NDCG Type Ranking Measures](https://mlsanity.com/paper/1304.6480/) (2013)
- [TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models](https://mlsanity.com/paper/2503.11656/) (2025)
- [Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey](https://mlsanity.com/paper/2406.05392/) (2024)
- [Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks](https://mlsanity.com/paper/2510.03667/) (2025)
- [Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy (with appendix)](https://mlsanity.com/paper/2306.10645/) (2023)
- [Learning to Prompt in the Classroom to Understand AI Limits: A pilot study](https://mlsanity.com/paper/2307.01540/) (2023)
- [Understanding Learner-LLM Chatbot Interactions and the Impact of Prompting Guidelines](https://mlsanity.com/paper/2504.07840/) (2025)
- [Use Me Wisely: AI-Driven Assessment for LLM Prompting Skills Development](https://mlsanity.com/paper/2503.02532/) (2025)
- [A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy](https://mlsanity.com/paper/2601.18939/) (2026)
- [Agentic AI as Undercover Teammates: Argumentative Knowledge Construction in Hybrid Human-AI Collaborative Learning](https://mlsanity.com/paper/2512.08933/) (2025)

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

- [Designing Human-mediated AI Guidance: Ready Together for Personalized Family Emergency Preparedness](https://mlsanity.com/paper/2608.19950/) (2026)

## Abstract (arXiv)

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.