让大模型基于个人数据图谱做个性化饮食建议。
Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary Recommendations
- 构建用户专属因果图，融合长期健康数据
- 生成建议后模拟血糖变化，降低餐后血糖曲线下面积
- 适合需要精准健康管理的医疗场景
大型语言模型（LLMs）擅长利用通用常识进行推理，但在需要处理多因素个人数据的个性化任务中仍存在局限。这一缺陷限制了其在医疗等需个体化决策领域的应用。本文提出个性化因果图推理框架，使LLM能够基于纵向数据构建用户特定的因果图，编码各类个人因素对目标结果的影响。面对查询时，模型通过图结构识别相关因果路径，按影响程度排序，模拟潜在结果并生成定制化响应。我们在以营养为导向的饮食建议场景中实现该框架，因代谢反应差异需个性化推理。通过反事实评估，验证了生成食物建议在控制血糖方面的有效性。相比先前方法，本方法在三个时间窗口内均降低了餐后血糖iAUC。额外的LLM作为裁判评估也证实了个性化质量的提升。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel at general-purpose reasoning by leveraging broad commonsense knowledge, but they remain limited in tasks requiring personalized reasoning over multifactorial personal data. This limitation constrains their applicability in domains such as healthcare, where decisions must adapt to individual contexts. We introduce Personalized Causal Graph Reasoning, a framework that enables LLMs to reason over individual-specific causal graphs constructed from longitudinal data. Each graph encodes how user-specific factors influence targeted outcomes. In response to a query, the LLM traverses the graph to identify relevant causal pathways, rank them by estimated impact, simulate potential outcomes, and generate tailored responses. We implement this framework in the context of nutrient-oriented dietary recommendations, where variability in metabolic responses demands personalized reasoning. Using counterfactual evaluation, we assess the effectiveness of LLM-generated food suggestions for glucose control. Our method reduces postprandial glucose iAUC across three time windows compared to prior approaches. Additional LLM-as-a-judge evaluations further confirm improvements in personalization quality.
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。