TheRegister's platform is a leading technology news website, offering insights into IT industry news, hardware reviews, and software updates. Through articles, analysis, and opinion pieces, TheRegister offers insights into cybersecurity threats, technology trends, and industry developments. Readers can stay updated with the latest news and analysis from the world of technology and IT business.

The Register

A USC research paper finds that persona-based prompting — telling an LLM it is an expert — actually hurts performance on factual and coding tasks while improving alignment-dependent tasks like safety and writing. On the MMLU benchmark, expert personas reduced accuracy from 71.6% to 68.0%. The explanation is that persona prefixes activate instruction-following mode at the expense of factual recall. The researchers propose PRISM, a gated LoRA mechanism that selectively applies persona-based behavior only where it helps, falling back to the base model for knowledge-dependent tasks. The practical takeaway: for accuracy and facts, skip the persona; for alignment, safety, or structured output, specific persona guidance can help.

Telling an AI model that it's an expert makes it worse

<p>So, I’ve been doing something right, even though I wasn’t following the mainstream… Business as usual. 👍</p>
