AI RESEARCH
PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users
arXiv CS.CL
•
ArXi:2605.13307v1 Announce Type: new Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions about how users and their simulated counterparts differ in interaction patterns and judgements, as well as whether personalisation is best achieved through context-based prompting or weight-based fine-tuning.