Thought-Like-Pro：通过自驱动的基于 Prolog 的思维链增强大型语言模型的推理能力
Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Bootstrapped Prolog-based Chain-of-Thought
AI总结：
本文提出 THOUGHT-LIKE-PRO 框架，让 LLM 自驱动地借助 Prolog 生成、验证并转换推理轨迹为自然语言 CoT 进行模仿学习，从而提升推理与分布外泛化能力。
摘要：
大型语言模型（LLM）作为通用助手已展现出卓越性能，在多种推理任务中表现突出。这一成就代表着迈向实现人工通用智能（AGI）的重要一步。尽管取得了这些进展，LLM 的有效性往往取决于所采用的具体提示策略，并且仍缺乏一个稳健的框架来促进跨多种推理任务的学习与泛化。为应对这些挑战，我们提出了一种新颖的学习框架 THOUGHT-LIKE-PRO。在该框架中，我们利用模仿学习来模仿思维链（CoT）过程，该过程由符号化 Prolog 逻辑引擎生成的推理轨迹经过验证和转换而来。该框架以自驱动方式运行，使 LLM 能够根据给定指令构造规则和语句，并利用符号化 Prolog 引擎推导结果。随后，LLM 将 Prolog 推导出的连续推理轨迹转换为自然语言 CoT，以进行模仿学习。我们的实证结果表明，所提出的方法显著增强了 LLM 的推理能力，并在分布外推理任务上展现出稳健的泛化能力。
英文摘要：
Large language models have demonstrated remarkable capabilities as general-purpose assistants, excelling in a wide range of reasoning tasks and supporting various aspects of daily web usage. This achievement represents a significant step toward achieving artificial general intelligence. Despite these advancements, the effectiveness of large language models often hinges on the specific prompting strategies employed, and there remains a lack of a robust framework to facilitate learning and generalization across diverse reasoning tasks. To address these challenges, we introduce a novel learning framework, Thought-Like-Pro. In this framework, we utilize imitation learning to imitate the Chain-of-Thought process which is verified and translated from reasoning trajectories generated by a symbolic Prolog logic engine. This framework proceeds in a prompt-guided but self-bootstrapped manner, that enables large language models to formulate rules and statements from given instructions and leverage the symbolic Prolog engine to derive results. Subsequently, large language models convert Prolog-derived successive reasoning trajectories into natural language chain-of-thought for imitation learning. The empirical findings indicate that our proposed approach greatly improves the reasoning capacity of large language models. By employing model averaging techniques, our method exhibits only a marginal decline in performance for distributional extrapolation tasks, showing robust generalization capabilities. We present a technical approach that integrates symbolic reasoning with language modeling, with the potential to support the development of large language models as cognitively inspired systems. The part of the dataset we used has been open-sourced.
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。
