Jennifer Haase

Structured Creativity Methods for Multi-Agent LLMs: Brainwriting Outperforms Disney and Double Diamond on LLM-Judged Originality

The Missing Drive: Functional Analogs of Intrinsic Motivation in Large Language Models for Creative Tasks

Prompting Against Persona Drift: Comparing Intervention Timing and Content in LLM-Simulated Conversations

Simulating student personas with large language models (LLMs) enables scalable evaluation of educational systems. However, behavioral drift, a progressive decline in persona consistency, can emerge over extended conversations, limiting the validity of such simulations. We evaluate five prompt-level mechanisms using sep...

Negotiating epistemic authority in the age of generative AI: AI reliance, responsibility, and usage intensity among GenAI-using coaching professionals

The findings reveal that coaches report using GenAI extensively for structured, information-intensive tasks while maintaining control over relational and interpretative work, which can be understood as boundary work preserving human authority over domains of tacit expertise.