Logic-of-Thought：利用逻辑程序增强大语言模型解决自然语言谜题的能力
Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language
AI总结：
提出Logic-of-Thought框架，结合大语言模型与回答集程序，将自然语言谜题转为逻辑程序求解，在网格和动态谜题上达到近乎完美准确率。
摘要：
在自然语言中解决谜题是人工智能领域长期存在的挑战。尽管大语言模型（LLMs）近期在多种任务上展现出令人印象深刻的能力，但它们仍难以应对需要精确推理和穷举搜索的复杂谜题。在本文中，我们提出Logic-of-Thought（Logot），一种将LLMs与逻辑编程相结合的新框架，以解决这一问题。我们的方法利用LLMs将谜题规则和状态转换为回答集程序（ASPs），随后由ASP解释器准确且高效地推断出这些程序的解。这种混合方法结合了LLMs的自然语言理解能力与逻辑程序的精确推理能力。我们在多种网格谜题和涉及动作的动态谜题上评估了我们的方法，在所有任务上展示了近乎完美的准确性。我们的代码和数据可在以下网址获取：https://github.com/naiqili/Logic-of-Thought。
英文摘要：
Solving puzzles in natural language poses a long-standing challenge in AI. While large language models (LLMs) have recently shown impressive capabilities in a variety of tasks, they continue to struggle with complex puzzles that demand precise reasoning and exhaustive search. In this paper, we propose Logic-of-Thought (Logot), a novel framework that bridges LLMs with logic programming to address this problem. Our method leverages LLMs to translate puzzle rules and states into answer set programs (ASPs), the solution of which are then accurately and efficiently inferred by an ASP interpreter. This hybrid approach combines the natural language understanding of LLMs with the precise reasoning capabilities of logic programs. We evaluate our method on various grid puzzles and dynamic puzzles involving actions, demonstrating near-perfect accuracy across all tasks. Our code and data are available at: https://github.com/naiqili/Logic-of-Thought.
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。
