Large Language Models (LLMs) can propose rules in natural language, sidestepping the need for a predefined predicate space in traditional rule learning. Yet many LLM-based approaches ignore interactions among rules, and the opportunity to couple LLMs with probabilistic rule learning for robust inference remains underexplored. We present RLIE, a unified framework that integrates LLMs with probabilistic modeling to learn a set of weighted rules. RLIE has four stages: (1) Rule generation, where an LLM proposes and filters candidates; (2) Logistic regression, which learns probabilistic weights for global selection and calibration; (3) Iterative refinement, which updates the rule set using prediction errors; and (4) Evaluation, which compares the weighted rule set as a direct classifier with methods that inject rules into an LLM. We evaluate multiple inference strategies on real-world datasets. Applying rules directly with their learned weights yields superior performance, whereas prompting LLMs with the rules, weights, and logistic-model outputs surprisingly degrades accuracy. This supports the view that LLMs excel at semantic generation and interpretation but are less reliable for precise probabilistic integration. RLIE clarifies the potential and limitations of LLMs for inductive reasoning and couples them with classic probabilistic rule combination methods to enable more reliable neuro-symbolic reasoning.

翻译：大语言模型（LLM）能够以自然语言形式提出规则，从而规避了传统规则学习中预定义谓词空间的需求。然而，许多基于LLM的方法忽略了规则间的相互作用，且将LLM与概率化规则学习相结合以实现稳健推理的潜力仍未得到充分探索。本文提出RLIE，一个将LLM与概率建模相融合的统一框架，用于学习一组加权规则。RLIE包含四个阶段：（1）规则生成：由LLM提出并筛选候选规则；（2）逻辑回归：通过概率权重学习实现全局选择与校准；（3）迭代优化：依据预测误差更新规则集；（4）评估：将加权规则集作为直接分类器，与将规则注入LLM的方法进行比较。我们在真实数据集上评估了多种推理策略。实验表明，直接应用带有学习权重的规则可获得更优性能，而将规则、权重及逻辑模型输出通过提示方式输入LLM反而会降低准确性。这支持了以下观点：LLM擅长语义生成与解释，但在精确的概率整合方面可靠性较低。RLIE阐明了LLM在归纳推理中的潜力与局限，并将其与经典的概率规则组合方法相结合，为实现更可靠的神经符号推理提供了新途径。