从假设到前提：基于大语言模型的反向逻辑推理与选择性符号翻译
From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation
AI总结：
本文提出HBLR框架，通过结合自信符号翻译与假设驱动反向推理，提升逻辑推理的准确性和效率。
摘要：
逻辑推理是自然语言理解中的核心挑战，也是人工智能的基本能力，支撑着科学发现、数学定理证明和复杂决策制定。尽管大语言模型（LLMs）取得了显著进展，但大多数现有方法仍依赖于正向推理范式，从前提生成逐步推理过程。然而，此类方法常面临冗余的推理路径、幻觉步骤和语义漂移，导致推理效率低下且不可靠。在本文中，我们提出了一种新的框架，即假设驱动的反向逻辑推理（HBLR）。核心思想是将具有信心的符号翻译与假设驱动的反向推理相结合。在翻译阶段，只有高置信度的片段才会转换为逻辑形式，如一阶逻辑（FOL），而不确定的内容仍保留为自然语言。翻译反思模块进一步通过评估符号输出并必要时将其改回文本，确保语义忠实。在推理阶段，HBLR通过假设结论为真并递归验证其前提来模拟人类的演绎思维。推理反思模块进一步识别并纠正错误的推理步骤，提高逻辑连贯性。在五个推理基准上的广泛实验表明，HBLR在准确性和效率上均优于强大的基线模型。
英文摘要：
Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical theorem proving, and complex decision-making. Despite the remarkable progress of large language models (LLMs), most current approaches still rely on forward reasoning paradigms, generating step-by-step rationales from premises to conclusions. However, such methods often suffer from redundant inference paths, hallucinated steps, and semantic drift, resulting in inefficient and unreliable reasoning. In this paper, we propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR). The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning. In the translation phase, only high-confidence spans are converted into logical form, such as First-Order Logic (FOL), while uncertain content remains in natural language. A translation reflection module further ensures semantic fidelity by evaluating symbolic outputs and reverting lossy ones back to text when necessary. In the reasoning phase, HBLR simulates human deductive thinking by assuming the conclusion is true and recursively verifying its premises. A reasoning reflection module further identifies and corrects flawed inference steps, enhancing logical coherence. Extensive experiments on five reasoning benchmarks demonstrate that HBLR consistently outperforms strong baselines in both accuracy and efficiency.
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。
