PICLe：通过人格化上下文学习从大语言模型中激发多样化行为
PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning
AI总结：
本研究形式化人格激发任务，提出基于贝叶斯推理的PICLe框架，通过似然比准则选择ICL示例来引导大语言模型激发目标人格，在三种主流LLM上验证了有效性并开源代码。
摘要：
大语言模型（LLMs）在大规模文本语料库上训练，这些语料编码了多样的人格特质，这催生了从LLM中激发目标人格特质并探究其行为偏好的研究目标。据此，我们将人格激发任务形式化，旨在定制LLM行为以匹配目标人格。我们提出了人格化上下文学习（PICLe），这是一种基于贝叶斯推理的新型人格激发框架。其核心是PICLe引入了一种基于似然比的全新ICL示例选择准则，旨在最优地引导模型激发特定目标人格。我们通过在三种主流LLM上与基线方法进行广泛对比，验证了PICLe的有效性。代码可在https://github.com/deeplearning-wisc/picle获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
