May 3, 2024Open Access

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

Key Points

PICLe effectively customizes large language model behaviors based on specific personality traits, enhancing user interaction.
The novel method utilizes a likelihood ratio for selecting in-context learning examples, optimizing persona elicitation.
Extensive comparisons against baseline methods show significant improvements across three contemporary large language models, indicating broad applicability of the framework in practice. Code availability at GitHub enables further exploration and adaptation by the community for diverse tasks and purposes.

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.

Read Full Paperexternally

KI fragen

Bookmark

View Full Paper