推进大型语言模型中的推理：有前景的方法与途径
Advancing Reasoning in Large Language Models: Promising Methods and Approaches
AI总结：
本综述全面回顾了增强大型语言模型推理能力的新兴技术，涵盖提示策略、架构创新与学习范式，并探讨了评估框架及开放挑战，为未来研究与应用提供方向。
摘要：
大型语言模型（LLMs）在各种自然语言处理（NLP）任务中取得了显著成功，但其推理能力仍是一个根本性挑战。尽管LLMs展现出令人印象深刻的流畅性和事实回忆能力，但它们执行复杂推理的能力——涵盖逻辑演绎、数学问题求解、常识推断和多步推理——往往达不到人类的期望。本综述对增强LLMs推理能力的新兴技术进行了全面回顾。我们将现有方法分类为关键途径，包括提示策略（例如，思维链推理、自洽性和思维树推理）、架构创新（例如，检索增强模型、模块化推理网络和神经符号集成）以及学习范式（例如，使用推理特定数据集进行微调、强化学习和自监督推理目标）。此外，我们探讨了用于评估LLMs推理能力的评估框架，并强调了开放性挑战，如幻觉、鲁棒性以及跨不同任务的推理泛化。通过综合近期的进展，本综述旨在为推理增强LLMs的未来研究和实际应用提供有前景的方向见解。
英文摘要：
Large Language Models (LLMs) have succeeded remarkably in various natural language processing (NLP) tasks, yet their reasoning capabilities remain a fundamental challenge. While LLMs exhibit impressive fluency and factual recall, their ability to perform complex reasoning-spanning logical deduction, mathematical problem-solving, commonsense inference, and multi-step reasoning-often falls short of human expectations. This survey provides a comprehensive review of emerging techniques enhancing reasoning in LLMs. We categorize existing methods into key approaches, including prompting strategies (e.g., Chain-of-Thought reasoning, Self-Consistency, and Tree-of-Thought reasoning), architectural innovations (e.g., retrieval-augmented models, modular reasoning networks, and neuro-symbolic integration), and learning paradigms (e.g., fine-tuning with reasoning-specific datasets, reinforcement learning, and self-supervised reasoning objectives). Additionally, we explore evaluation frameworks used to assess reasoning in LLMs and highlight open challenges, such as hallucinations, robustness, and reasoning generalization across diverse tasks. By synthesizing recent advancements, this survey aims to provide insights into promising directions for future research and practical applications of reasoning-augmented LLMs.
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。
