Beyond Helpfulness and Harmlessness: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning

arXiv:2405.02501v1 Announce Type: new
Abstract: Large Language Models (LLMs) are trained on massive text corpora, which are encoded with diverse personality traits. This triggers an interesting goal of eliciting a desired personality trait from the LLM, and probing its behavioral preferences. Accordingly, we formalize the persona elicitation task, aiming to customize LLM behaviors to align with a target persona. We present Persona In-Context Learning (PICLe), a novel persona elicitation framework grounded in Bayesian inference. At the core, PICLe introduces a …

arxiv beyond context context learning cs.ai cs.cl diverse in-context learning language language models large language large language models type