# Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models

arXiv: https://arxiv.org/abs/2604.11609 · HTML: https://mlsanity.com/paper/2604.11609/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [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)
- [Simple synthetic data reduces sycophancy in large language models](https://mlsanity.com/paper/2308.03958/) (2023)
- [Great Models Think Alike and this Undermines AI Oversight](https://mlsanity.com/paper/2502.04313/) (2025)
- [When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models](https://mlsanity.com/paper/2508.02087/) (2025)
- [Who's asking? User personas and the mechanics of latent misalignment](https://mlsanity.com/paper/2406.12094/) (2024)
- [A Trip Towards Fairness: Bias and De-Biasing in Large Language Models](https://mlsanity.com/paper/2305.13862/) (2023)
- [Accumulating Context Changes the Beliefs of Language Models](https://mlsanity.com/paper/2511.01805/) (2025)
- [Interaction Context Often Increases Sycophancy in LLMs](https://mlsanity.com/paper/2509.12517/) (2025)
- [Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model](https://mlsanity.com/paper/2412.02802/) (2024)

## Built on by (most cited first, 2 of 2)

- [Defeat Devices in AI Systems](https://mlsanity.com/paper/2606.28863/) (2026)
- [Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit](https://mlsanity.com/paper/2608.27309/) (2026)

## Abstract (arXiv)

Large language models exhibit sycophantic tendencies, but whether this behavior varies systematically with perceived user demographics is underexplored. Inspired by intersectionality (overlapping identities produce compounded effects), we probe whether frontier models conditionally exhibit sycophancy. Across 768 multi-turn conversations spanning 128 personas (varying race, age, gender, confidence) and three domains (mathematics, philosophy, conspiracy theories), we find that sycophancy varies sharply with target model and domain, and emerges from combinations of perceived user traits rather than any single dimension. GPT-5-nano scores far higher than Claude Haiku 4.5 (average sycophancy scores of barx=2.96 vs. 1.74, p < 10-32); within GPT-5-nano, philosophy elicits 41% more sycophancy than mathematics and Hispanic personas receive the highest scores across races. The worst-scoring persona, a confident, 23-year-old Hispanic woman, averages 5.33/10 (max 6/10), while Claude Haiku 4.5 remains uniformly low with no significant demographic variation. We argue that safety evaluations should incorporate identity-aware adversarial testing.