AI.info

Jan Batzner

Explore Jan Batzner on AI.info.

• One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization
• Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
• Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency
• Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
• Measuring what Matters: Construct Validity in Large Language Model Benchmarks