AI RESEARCH
The Impact of Steering Large Language Models with Persona Vectors in Educational Applications
arXiv CS.CL
•
ArXi:2604.07102v1 Announce Type: new Activation-based steering can personalize large language models at inference time, but its effects in educational settings remain unclear. We study persona vectors for seven character traits in short-answer generation and automated scoring on the ASAP-SAS benchmark across three models spanning two architectures. Persona steering lowers answer quality overall, with much larger effects on open-ended English Language Arts (ELA) prompts than on factual science prompts; interpretive and argumentative tasks are up to 11x sensitive.