通过显式分析用户画像提升营养咨询个性化效果
PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consulting
- 将用户画像解析作为独立推理步骤，增强个性化
- 在G-Eval评分中平均分达4.21，个人化与安全得分领先
- 适合需要精准个性化的健康咨询系统开发者
在健康与营养咨询中，现有提示方法通常以非结构化方式传递用户画像，缺乏专门分析步骤，导致个性化能力不足。本文提出PA-CoT（Profile-Adaptive Chain-of-Thought），一种多阶段提示方法，将画像解读作为生成回应前的独立推理步骤。为实现系统评估，我们构建了QPA（Question--Profile--Answer）基准，包含200个结构化用户画像的营养咨询样本，按四个标准评分。在与11种对比方法（包括CoT、Few-Shot、Role Prompting、DSPy、TextGrad、Self-Refine等及Zero-Shot基线）的比较中，PA-CoT取得最高平均分（G-Eval 1–5尺度下为4.21），并在个人化（4.71 vs. 4.39）与安全性（4.68 vs. 4.52）两项指标上均显著优于次优方法，且95%置信区间不重叠——是唯一同时在两项指标上领先的模型。结果表明，显式画像分析是提升个性化表现的关键。
原文摘要 · Abstract (English)
In health and nutrition consulting, widely used prompting methods pass the user profile as an unstructured block without a dedicated analysis step, leaving personalization as a critical structural gap. We introduce PA-CoT (Profile-Adaptive Chain-of-Thought), a multi-stage prompting method that treats profile interpretation as an explicit, standalone reasoning step prior to response generation. To enable systematic evaluation, we introduce the QPA (Question--Profile--Answer) benchmark -- 200 nutritional consulting samples with structured user profiles scored on four criteria. In a comparative study against 11 comparison methods (CoT, Few-Shot, Role Prompting, DSPy, TextGrad, Self-Refine, and others, plus a Zero-Shot Baseline; 12 total including PA-CoT), PA-CoT achieves the best average score (4.21 on the G-Eval 1--5 scale) and leads on both Personalization (4.71 vs. 4.39) and Safety (4.68 vs. 4.52) with non-overlapping 95\% confidence intervals over the nearest competitor -- the only method to simultaneously top both criteria. The results confirm that an explicit profile-analysis step is the key driver of personalization gains over widely used prompting approaches.
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。