Skip to yearly menu bar Skip to main content


Poster

PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning

Hyeong Kyu Choi · Sharon Li

Hall C 4-9 #807
[ ] [ Project Page ]
Wed 24 Jul 4:30 a.m. PDT — 6 a.m. PDT

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 new ICL example selection criterion based on likelihood ratio, which is designed to optimally guide the model in eliciting a specific target persona. We demonstrate the effectiveness of PICLe through extensive comparisons against baseline methods across three contemporary LLMs. Code is available at https://github.com/deeplearning-wisc/picle.

Live content is unavailable. Log in and register to view live content