通过本体引导的多智能体推理实现文化对齐的大型语言模型
Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
AI总结：
本文提出OG-MAR框架，通过本体引导的多智能体推理方法，提高大型语言模型在文化对齐和鲁棒性方面的性能，并生成更透明的推理轨迹。
摘要：
大型语言模型（LLMs）越来越多地支持文化敏感的决策制定，但往往由于预训练数据倾斜和缺乏结构化的价值表示而表现出不一致。现有方法虽然可以引导输出，但通常缺乏人口统计学基础，并将价值观视为独立的、无结构的信号，从而降低一致性和可解释性。我们提出OG-MAR，一种本体引导的多智能体推理框架。OG-MAR从世界价值观调查（WVS）中总结出响应特定的价值，并通过能力问题在固定分类法上提取关系来构建全球文化本体。在推理过程中，它检索与本体一致的关系和人口统计学相似的资料，以实例化多个价值-人设代理，其输出由一个执行本体一致性和人口统计学接近性的判断代理合成。在四个LLM基础架构上的区域社会调查基准测试中，OG-MAR在文化对齐和鲁棒性方面优于竞争基线，同时生成更透明的推理轨迹。
英文摘要：
Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured value representations. Existing methods can steer outputs, but often lack demographic grounding and treat values as independent, unstructured signals, reducing consistency and interpretability. We propose OG-MAR, an Ontology-Guided Multi-Agent Reasoning framework. OG-MAR summarizes respondent-specific values from the World Values Survey (WVS) and constructs a global cultural ontology by eliciting relations over a fixed taxonomy via competency questions. At inference time, it retrieves ontology-consistent relations and demographically similar profiles to instantiate multiple value-persona agents, whose outputs are synthesized by a judgment agent that enforces ontology consistency and demographic proximity. Experiments on regional social-survey benchmarks across four LLM backbones show that OG-MAR improves cultural alignment and robustness over competitive baselines, while producing more transparent reasoning traces.
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。
