用分层因子构建可靠概率推断，解决大模型在信息不全时的预测盲区问题。
ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models
- 通过迭代生成与聚类构建密集分层因子空间
- 未知预测率显著降低，性能优于直接使用大模型的基线
- 适合需要高可靠性概率输出的应用场景
大规模决策中应对信息不完整的核心挑战是估计可靠的概率。现有方法利用大语言模型（LLMs）生成解释性因素和粗粒度概率估计，再由朴素贝叶斯模型对因子组合进行优化。然而，稀疏因子空间常导致“未知”预测，扩展因子则引入噪声与虚假相关，破坏条件独立性，降低可靠性。为此，我们提出 extsc{Anchor}，一个基于分层因子空间的聚合贝叶斯推理框架。它通过迭代生成与聚类构建稠密因子层次结构，利用分层检索与精炼映射上下文，并在朴素贝叶斯基础上引入因果贝叶斯网络以建模潜在因子依赖关系。实验表明， extsc{Anchor} 显著减少“未知”预测，生成的概率估计更可靠，性能达到当前最优，同时大幅降低时间和令牌开销。
原文摘要 · Abstract (English)
A central challenge in large-scale decision-making under incomplete information is estimating reliable probabilities. Recent approaches use Large Language Models (LLMs) to generate explanatory factors and coarse-grained probability estimates, which are then refined by a Naïve Bayes model over factor combinations. However, sparse factor spaces often yield ``unknown'' predictions, while expanding factors increases noise and spurious correlations, weakening conditional independence and degrading reliability. To address these limitations, we propose \textsc{Anchor}, an aggregated Bayesian inference framework over a hierarchical factor space. It constructs dense factor hierarchies through iterative generation and clustering, maps contexts via hierarchical retrieval and refinement, and augments Naïve Bayes with a Causal Bayesian Network to model latent factor dependencies. Experiments show that \textsc{Anchor} markedly reduces ``unknown'' predictions and produces more reliable probability estimates than direct LLM baselines, achieving state-of-the-art performance while significantly reducing time and token overhead.
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。