与逻辑对齐：测量、评估和改进大型语言模型的逻辑偏好一致性
Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
AI总结：
本研究针对LLMs判断不一致问题，提出基于传递性等三个属性的逻辑偏好一致性评估框架，引入REPAIR技术提升一致性并保持人类偏好对齐，实验证明该框架可反映鲁棒性且改进后算法性能更好。
摘要：
大型语言模型（LLMs）被期望具备可预测性和可信度，以支持可靠的决策系统。然而当前LLMs的判断常存在不一致性。本研究将逻辑偏好一致性视为构建更可靠LLM系统的基础要求，确保决策稳定连贯，同时减少不稳定或矛盾的输出。为量化逻辑偏好一致性，我们提出基于传递性、交换性和否定不变性三个基本属性的通用评估框架。通过在多种LLMs上的广泛实验，我们证明这些属性是判断鲁棒性的强指标。此外，我们引入数据细化和增强技术REPAIR，在保持与人类偏好对齐的同时提升逻辑一致性。最后，我们表明提高一致性可提升LLM驱动的基于逻辑的算法性能，增强决策系统的稳定性和连贯性。
英文摘要：
Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems. Yet current LLMs often show inconsistencies in their judgments. In this work, we examine logical preference consistency as a foundational requirement for building more dependable LLM systems, ensuring stable and coherent decision-making while minimizing erratic or contradictory outputs. To quantify the logical preference consistency, we propose a universal evaluation framework based on three fundamental properties: transitivity, commutativity and negation invariance. Through extensive experimentation across diverse LLMs, we demonstrate that these properties serve as strong indicators of judgment robustness. Furthermore, we introduce a data refinement and augmentation technique, REPAIR, that enhances logical consistency while maintaining alignment with human preferences. Finally, we show that improving consistency leads to better performance in LLM-driven logic-based algorithms, reinforcing stability and coherence in decision-making systems.
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。
