逻辑参数化神经符号推理：通过可控逻辑形式实现可验证的大语言模型推理
Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning
AI总结：
本文提出逻辑参数化框架，通过可控逻辑形式提升神经符号推理的鲁棒性与适应性，实验表明内部逻辑策略在不同领域具有更优表现。
摘要：
大型语言模型（LLMs）和定理证明器（TPs）可以有效结合用于可验证的自然语言推理（NLI）。然而，现有方法依赖于固定的逻辑形式，这一特性限制了鲁棒性和适应性。我们提出了一种逻辑参数化框架，用于神经符号NLI，将底层逻辑不视为静态背景，而是作为可控组件。使用LogiKEy方法，我们将一系列经典和非经典形式化嵌入到高阶逻辑（HOL）中，从而能够系统地比较推理质量、解释细化和证明行为。我们专注于规范推理，其中逻辑的选择具有重大影响。特别是，我们比较了逻辑外部方法，其中规范要求通过公理编码，与逻辑内部方法，其中规范模式从逻辑的内置结构中涌现。大量实验表明，逻辑内部策略能够一致地提高性能，并产生更高效的NLI混合证明。此外，我们还展示了逻辑的有效性取决于领域，一阶逻辑在常识推理中占优，而规范逻辑和模态逻辑在伦理领域表现优异。我们的结果强调了在神经符号架构中将逻辑作为第一类、参数化元素的价值，以实现更稳健、模块化和适应性强的推理。
英文摘要：
Large language models (LLMs) and theorem provers (TPs) can be effectively combined for verifiable natural language inference (NLI). However, existing approaches rely on a fixed logical formalism, a feature that limits robustness and adaptability. We propose a logic-parametric framework for neuro-symbolic NLI that treats the underlying logic not as a static background, but as a controllable component. Using the LogiKEy methodology, we embed a range of classical and non-classical formalisms into higher-order logic (HOL), enabling a systematic comparison of inference quality, explanation refinement, and proof behavior. We focus on normative reasoning, where the choice of logic has significant implications. In particular, we compare logic-external approaches, where normative requirements are encoded via axioms, with logic-internal approaches, where normative patterns emerge from the logic's built-in structure. Extensive experiments demonstrate that logic-internal strategies can consistently improve performance and produce more efficient hybrid proofs for NLI. In addition, we show that the effectiveness of a logic is domain-dependent, with first-order logic favouring commonsense reasoning, while deontic and modal logics excel in ethical domains. Our results highlight the value of making logic a first-class, parametric element in neuro-symbolic architectures for more robust, modular, and adaptable reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
