IROTE: 通过上下文自我反思优化 elicite 大语言模型的人类特质
IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization
AI总结：
IROTE通过上下文自我反思优化方法，使LLMs在多样任务中稳定体现人类特质，超越现有基线。
摘要：
在各种人类撰写的语料库上进行训练，大型语言模型（LLMs）已经展示了通过提示来反映特定人类特质（例如个性或价值观）的能力，这有利于个性化LLMs和社会模拟等应用。然而，现有方法存在表面提取问题：LLMs只能被引导去模仿浅层和不稳定的风格模式，无法在多样任务中如人类一样精确且一致地体现期望的特质。为了解决这一挑战，我们提出了IROTE，一种新颖的上下文方法，用于稳定和可迁移的特质提取。基于心理理论，认为特质是通过身份相关的反思形成的，我们的方法自动在提示中生成和优化一个文本自我反思，包括自我感知的经验，以刺激LLMs的特质驱动行为。优化是通过迭代最大化一个信息论目标来完成的，该目标增强了LLMs的行为与目标特质之间的联系，同时在不进行微调的情况下减少了反思中的噪声冗余，从而产生生动且紧凑的特质反思。在三个人类特质系统上进行的广泛实验表明，一个单一的IROTE生成的自我反思可以诱导LLMs在多样下游任务中稳定地扮演目标特质，超越简单的问卷回答，一致地优于现有强大的基线。
英文摘要：
Trained on various human-authored corpora, Large Language Models (LLMs) have demonstrated a certain capability of reflecting specific human-like traits (e.g., personality or values) by prompting, benefiting applications like personalized LLMs and social simulations. However, existing methods suffer from the superficial elicitation problem: LLMs can only be steered to mimic shallow and unstable stylistic patterns, failing to embody the desired traits precisely and consistently across diverse tasks like humans. To address this challenge, we propose IROTE, a novel in-context method for stable and transferable trait elicitation. Drawing on psychological theories suggesting that traits are formed through identity-related reflection, our method automatically generates and optimizes a textual self-reflection within prompts, which comprises self-perceived experience, to stimulate LLMs' trait-driven behavior. The optimization is performed by iteratively maximizing an information-theoretic objective that enhances the connections between LLMs' behavior and the target trait, while reducing noisy redundancy in reflection without any fine-tuning, leading to evocative and compact trait reflection. Extensive experiments across three human trait systems manifest that one single IROTE-generated self-reflection can induce LLMs' stable impersonation of the target trait across diverse downstream tasks beyond simple questionnaire answering, consistently outperforming existing strong baselines.
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。
