让大模型代理根据社会价值自动选择行为，提升决策合理性。
From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agents
- 用GraphRAG将社会价值观转为可执行指令
- 在DAILYDILEMMAS上表现优于多个基线方法
- 适合研究具身智能与伦理对齐的学者
基于大模型的智能体广泛应用需与人类社会价值对齐。当前方法在自我认知、困境决策和自我情绪方面仍存在不足。为此，我们提出一种基于价值的框架，利用GraphRAG将理论原则转化为价值导向指令，并在特定对话情境下检索合适指令以引导智能体行为。通过在基准数据集DAILYDILEMMAS上的实验，该方法显著优于提示工程基线（包括ECoT、Plan-and-Solve、Metacognitive prompting）。所提方法为人工智能系统中自我情绪的产生提供了基础。
原文摘要 · Abstract (English)
Wide applications of LLM-based agents require strong alignment with human social values. However, current works still exhibit deficiencies in self-cognition and dilemma decision, as well as self-emotions. To remedy this, we propose a novel value-based framework that employs GraphRAG to convert principles into value-based instructions and steer the agent to behave as expected by retrieving the suitable instruction upon a specific conversation context. To evaluate the ratio of expected behaviors, we define the expected behaviors from two famous theories, Maslow's Hierarchy of Needs and Plutchik's Wheel of Emotion. By experimenting with our method on the benchmark of DAILYDILEMMAS, our method exhibits significant performance gains compared to prompt-based baselines, including ECoT, Plan-and-Solve, and Metacognitive prompting. Our method provides a basis for the emergence of self-emotion in AI systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。