用概率图融合大模型与因果学习，提升因果关系推断准确率
LLM-Augmented Causal Discovery: Probabilistic Fusion of Edge Existence and Orientation
- 构建概率依赖图，将边存在性与方向性表示为概率分布
- 50/50融合使22个基准网络的F1值超越单一来源，平均提升0.056（p<0.001）
- 大模型擅长方向判断，传统算法擅长识别边骨架，二者互补
从观测数据中学习贝叶斯网络结构（BNSL）在方向可识别性上存在困难，而大语言模型（LLMs）虽具备广泛但不可靠的因果知识。本文提出通过一种新型表示——概率依赖图（PDGs），融合两者优势。在PDG中，每条边关联一个关于有向、无向和缺失状态的概率分布，实现加权平均融合。我们在26个基准网络上评估该方法，将三种BNSL算法（FGES、Tabu、PC）与三种LLMs（Gemini、Claude、GPT）的集成结果在多个提示和随机种子下进行组合。简单50/50融合在22个网络中优于任一单独源，平均F1提升0.056（p<0.001）。分析显示：BNSL提供高召回边骨架（80%对比LLM的60%），而LLM提供更准的方向判断（96%对比BNSL的77%）。结果表明，将两种来源统一表示为边存在性与方向性的概率不确定性，是提升因果图准确性的有效实用方法。
原文摘要 · Abstract (English)
Bayesian network structure learning (BNSL) from observational data struggles with orientation identifiability, while large language models (LLMs) offer broad but often unreliable causal knowledge. We propose combining these complementary sources through a novel representation, termed Probabilistic Dependency Graphs (PDGs). In a PDG, each edge is associated with a distribution over directed, undirected, and absent states, enabling fusion via weighted averaging. We evaluate this approach on 26 benchmark networks, combining ensembles of three BNSL algorithms (FGES, Tabu, PC) with three LLMs (Gemini, Claude, GPT) across multiple prompts and random seeds. A simple 50/50 fusion improves F1 over the better of either source alone in 22 of 26 networks, with a statistically significant mean improvement of $0.056$ $(p<0.001)$. Analysis reveals that the two sources play complementary roles: BNSL contributes a high-recall edge skeleton (80\% vs 60\% for LLM), while LLM contributes accurate edge orientation (96\% vs 77\% for BNSL). Our results show that representing both sources as probabilistic uncertainty over edge existence and orientation is a practical and effective way to improve causal graph accuracy.
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。