Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs

📄 arXiv: 2402.09836v2 📥 PDF

作者: Chenyang Shao, Fengli Xu, Bingbing Fan, Jingtao Ding, Yuan Yuan, Meng Wang, Yong Li

分类: cs.AI

发布日期: 2024-02-15 (更新: 2024-06-05)


💡 一句话要点

提出Chain-of-Planned Behaviour以解决人类行为生成问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 大型语言模型 计划行为理论 移动行为生成 重力模型 智能交通系统 人机交互 行为意图推理

📋 核心要点

  1. 现有方法在生成移动行为时未能充分考虑社会规范和个人偏好,导致生成结果的准确性不足。
  2. 本文提出的Chain-of-Planned Behaviour(CoPB)工作流程,基于计划行为理论,增强了LLMs对移动意图的推理能力。
  3. 实验结果表明,CoPB将移动意图生成的错误率从57.8%降低至19.4%,并且与重力模型结合后,显著降低了计算成本。

📝 摘要(中文)

大型语言模型(LLMs)在推理能力上取得了显著进展,但在生成人类行为方面的表现尚未得到充分探索。这一差距可能源于行为意图的内在过程不仅仅依赖于抽象推理,还受到社会规范和个人偏好的影响。受计划行为理论(TPB)的启发,本文提出了一种名为Chain-of-Planned Behaviour(CoPB)的工作流程,用于生成移动行为,反映人类活动的重要时空动态。通过利用TPB中的态度、主观规范和感知行为控制的认知结构,CoPB显著提高了LLMs推理下一步移动意图的能力,错误率从57.8%降低至19.4%。此外,CoPB与机械模型的协同作用也得到了探索,发现重力模型能够有效地将移动意图映射到物理移动行为。

🔬 方法详解

问题定义:本文旨在解决大型语言模型在生成移动行为时的准确性不足问题,现有方法未能充分考虑影响行为意图的多种因素,如社会规范和个人偏好。

核心思路:提出Chain-of-Planned Behaviour(CoPB)工作流程,利用计划行为理论中的认知结构,增强LLMs对移动意图的推理能力,从而提高生成的准确性。

技术框架:CoPB工作流程包括三个主要模块:态度模块、主观规范模块和感知行为控制模块,结合LLMs进行移动行为生成。

关键创新:CoPB的核心创新在于将计划行为理论的认知结构引入LLMs,显著提升了移动意图生成的准确性,与传统方法相比,错误率大幅降低。

关键设计:在模型设计中,采用了重力模型与CoPB的结合,优化了参数设置,减少了97.7%的计算成本,同时保持了生成行为的质量。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,CoPB工作流程将移动意图生成的错误率从57.8%降低至19.4%,并且与重力模型结合后,计算成本降低了97.7%。这些结果表明,CoPB在提高生成行为质量和效率方面具有显著优势。

🎯 应用场景

该研究的潜在应用领域包括智能交通系统、社交机器人和人机交互等。通过提高移动行为生成的准确性,CoPB能够在实际应用中更好地模拟人类行为,提升用户体验和系统效率,未来可能对智能系统的设计和优化产生深远影响。

📄 摘要(原文)

The powerful reasoning capabilities of large language models (LLMs) have brought revolutionary changes to many fields, but their performance in human behaviour generation has not yet been extensively explored. This gap likely emerges because the internal processes governing behavioral intentions cannot be solely explained by abstract reasoning. Instead, they are also influenced by a multitude of factors, including social norms and personal preference. Inspired by the Theory of Planned Behaviour (TPB), we develop a LLM workflow named Chain-of-Planned Behaviour (CoPB) for mobility behaviour generation, which reflects the important spatio-temporal dynamics of human activities. Through exploiting the cognitive structures of attitude, subjective norms, and perceived behaviour control in TPB, CoPB significantly enhance the ability of LLMs to reason the intention of next movement. Specifically, CoPB substantially reduces the error rate of mobility intention generation from 57.8% to 19.4%. To improve the scalability of the proposed CoPB workflow, we further explore the synergy between LLMs and mechanistic models. We find mechanistic mobility models, such as gravity model, can effectively map mobility intentions to physical mobility behaviours. The strategy of integrating CoPB with gravity model can reduce the token cost by 97.7% and achieve better performance simultaneously. Besides, the proposed CoPB workflow can facilitate GPT-4-turbo to automatically generate high quality labels for mobility behavior reasoning. We show such labels can be leveraged to fine-tune the smaller-scale, open source LLaMA 3-8B, which significantly reduces usage costs without sacrificing the quality of the generated behaviours.