ABSOL: Aggregated Bayesian Subsampling Orchestrated with LLMs

2026-09-14

AI Summary

为解决大型语言模型在处理结构化数据时的不确定性估计和依赖性推理问题，提出ABSOL框架，结合LLM与贝叶斯网络学习结构，提高Edge F_1分数。

Abstract

Large language models are increasingly used as natural-language interfaces to structured data, yet they remain unreliable when answers require consistent evidence conditioning, dependency-aware reasoning, and uncertainty estimation. Bayesian networks provide an explicit probabilistic reasoning layer, but learning useful structures from data remains costly and fragile at scale. We introduce ABSOL, a hybrid LLM-guided Bayesian network structure-learning framework that uses LLMs as bounded semantic guides. Across five discrete BN benchmarks spanning 27 to 1041 nodes, ABSOL is the only evaluated method to produce a viable graph on every benchmark, and achieves the highest Edge F_1 on every benchmark larger than 27 nodes with GPT-5.4. The four LLM augmentations, which contribute complementary semantic evidence to the statistical backbone, improve Edge F_1 over the non-LLM aggregation backbone by +0.23 on average. Complementary post-hoc refinement experiments suggest that these gains depend in part on limiting the LLM's authority over the final structure. Together, these results show that language-derived semantic knowledge can substantially improve scalable probabilistic structure learning when used as bounded guidance within a statistically grounded reasoning pipeline. The code for ABSOL is available at github.com/megagonlabs/absol-bn.

Problem

• Large language models
• Bayesian networks
• probabilistic reasoning
• structure learning
• uncertainty estimation

Innovation

• LLM-guided Bayesian network
• semantic guidance
• scalable probabilistic structure learning
• Edge F_1 improvement