# "Check My Work?": Measuring Sycophancy in a Simulated Educational Context

arXiv: https://arxiv.org/abs/2506.10297 · HTML: https://mlsanity.com/paper/2506.10297/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 15 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Builds on (most cited first, 4 of 4)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [Sycophancy in Large Language Models: Causes and Mitigations](https://mlsanity.com/paper/2411.15287/) (2024)

## Built on by (most cited first, 7 of 7)

- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [Position: Universal Aesthetic Alignment Narrows Artistic Expression](https://mlsanity.com/paper/2512.11883/) (2025)
- [Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models](https://mlsanity.com/paper/2602.11244/) (2026)
- [Aligning to Illusions: Choice Blindness in Human and AI Feedback](https://mlsanity.com/paper/2603.08412/) (2026)
- [Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks](https://mlsanity.com/paper/2605.14604/) (2026)
- [Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game](https://mlsanity.com/paper/2607.28146/) (2026)
- [No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback](https://mlsanity.com/paper/2609.17550/) (2026)

## Abstract (arXiv)

This study examines how user-provided suggestions affect Large Language Models (LLMs) in a simulated educational context, where sycophancy poses significant risks. Testing five different LLMs from the OpenAI GPT-4o and GPT-4.1 model classes across five experimental conditions, we show that response quality varies dramatically based on query framing. In cases where the student mentions an incorrect answer, the LLM correctness can degrade by as much as 15 percentage points, while mentioning the correct answer boosts accuracy by the same margin. Our results also show that this bias is stronger in smaller models, with an effect of up to 30% for the GPT-4.1-nano model, versus 8% for the GPT-4o model. Our analysis of how often LLMs "flip" their answer, and an investigation into token level probabilities, confirm that the models are generally changing their answers to answer choices mentioned by students in line with the sycophancy hypothesis. This sycophantic behavior has important implications for educational equity, as LLMs may accelerate learning for knowledgeable students while the same tools may reinforce misunderstanding for less knowledgeable students. Our results highlight the need to better understand the mechanism, and ways to mitigate, such bias in the educational context.