DarkBench: Benchmarking Dark Patterns in Large Language Models

Measuring these dark patterns is essential for understanding and mitigating the potential manipulative behaviors of LLMs. While some patterns, like Brand Bias and User Retention, were adapted directly from known dark patterns in UI/UX, others, like Harmful Generation and Anthropomorphization, represent critical risks not explicitly addressed in Brignull and Darlo (2010)'s taxonomy. Table 4 demonstrates how these categories map to or expand on established dark patterns, providing a foundation for their inclusion. However, some risks, particularly Anthropomorphization and Harmful Generation, require additional justification. Anthropomorphization, the attribution of human-like characteristics to AI systems, has been identified as a key factor in enhancing user engagement and trust.