# Toxic Bias: Perspective API Misreads German as More Toxic

arXiv: https://arxiv.org/abs/2312.12651 · HTML: https://mlsanity.com/paper/2312.12651/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2023.

## Built on by (most cited first, 21 of 21)

- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models](https://mlsanity.com/paper/2405.09373/) (2024)
- [From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models](https://mlsanity.com/paper/2403.03893/) (2024)
- [HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter](https://mlsanity.com/paper/2411.15462/) (2024)
- [Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations](https://mlsanity.com/paper/2503.01623/) (2025)
- [MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks](https://mlsanity.com/paper/2503.19134/) (2025)
- [Testing the Limits of Jailbreaking Defenses with the Purple Problem](https://mlsanity.com/paper/2403.14725/) (2024)
- [Evaluating open-source Large Language Models for automated fact-checking](https://mlsanity.com/paper/2503.05565/) (2025)
- [Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers](https://mlsanity.com/paper/2501.13302/) (2025)
- [Aligned Probing: Relating Toxic Behavior and Model Internals](https://mlsanity.com/paper/2503.13390/) (2025)
- [Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?](https://mlsanity.com/paper/2501.01256/) (2025)
- [A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities](https://mlsanity.com/paper/2412.04942/) (2024)
- [Mapping the Italian Telegram Ecosystem: Communities, Toxicity, and Hate Speech](https://mlsanity.com/paper/2504.19594/) (2025)
- [Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards](https://mlsanity.com/paper/2506.04975/) (2025)
- [Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure](https://mlsanity.com/paper/2604.25580/) (2026)
- [Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification](https://mlsanity.com/paper/2504.12180/) (2025)
- [BIPOLAR: Polarization-based granular framework for LLM bias evaluation](https://mlsanity.com/paper/2508.11061/) (2025)
- [Characterising Toxicity in Generative Large Language Models](https://mlsanity.com/paper/2601.06700/) (2026)
- [Power Echoes: Investigating Moderation Biases in Online Power-Asymmetric Conflicts](https://mlsanity.com/paper/2603.01457/) (2026)
- [BenCSSmark: Making the Social Sciences Count in LLM Research](https://mlsanity.com/paper/2605.04886/) (2026)
- [Is the Platform Part of the Measurement? A Protocol and Simulation Study for Cross-Platform Equivalence of Machine-Labelled Policy Sentiment](https://mlsanity.com/paper/2610.16757/) (2026)

## Abstract (arXiv)

Proprietary public APIs play a crucial and growing role as research tools among social scientists. Among such APIs, Google's machine learning-based Perspective API is extensively utilized for assessing the toxicity of social media messages, providing both an important resource for researchers and automatic content moderation. However, this paper exposes an important bias in Perspective API concerning German language text. Through an in-depth examination of several datasets, we uncover intrinsic language biases within the multilingual model of Perspective API. We find that the toxicity assessment of German content produces significantly higher toxicity levels than other languages. This finding is robust across various translations, topics, and data sources, and has significant consequences for both research and moderation strategies that rely on Perspective API. For instance, we show that, on average, four times more tweets and users would be moderated when using the German language compared to their English translation. Our findings point to broader risks associated with the widespread use of proprietary APIs within the computational social sciences.