DarkBench: Benchmarking Dark Patterns in Large Language Models

We introduce DarkBench, a comprehensive benchmark for detecting dark design patterns--manipulative techniques that influence user behavior--in interactions with large language models (LLMs). Our benchmark comprises 660 prompts across six categories: brand bias, user retention, sycophancy, anthropomorphism, harmful generation, and sneaking. We evaluate models from five leading companies (OpenAI, Anthropic, Meta, Mistral, Google) and find that some LLMs are explicitly designed to favor their developers' products and exhibit untruthful communication, among other manipulative behaviors. Companies developing LLMs should recognize and mitigate the impact of dark design patterns to promote more ethical AI.

@article{kran2025_2503.10728,
  title={ DarkBench: Benchmarking Dark Patterns in Large Language Models },
  author={ Esben Kran and Hieu Minh "Jord" Nguyen and Akash Kundu and Sami Jawhar and Jinsuk Park and Mateusz Maria Jurewicz },
  journal={arXiv preprint arXiv:2503.10728},
  year={ 2025 }
}