ACIL: 自动链式思维用于上下文学习
ACIL: Auto Chain of Thoughts for In-Context Learning
AI总结：
本文提出ACIL框架，通过自动构建包含推理步骤的演示来提升上下文学习在多步推理任务中的性能。
摘要：
近年来，大型语言模型（LLMs）的进步表明，链式思维（CoT）推理可以显著提高复杂推理任务的性能。同时，上下文学习（ICL）已成为一种重要的机制，用于在不更新模型参数的情况下将LLMs适应于新任务，仅使用提示中提供的示例。然而，标准ICL在需要多步推理的任务上往往表现不佳，因为演示通常只包含输入-输出对，缺乏显式的中间推理步骤。本文介绍了一种自动链式思维（Auto-CoT）框架，通过自动构建推理增强的演示来改进ICL。Auto-CoT为输入-输出示例生成推理链，将结构化的中间解释添加到提示上下文中，并通过系统化的选择过程去除无关或低质量的演示。通过将高质量的推理示例纳入ICL提示中，Auto-CoT引导模型朝向更可靠的推理，并提高预测准确性。在多个推理任务上的实验表明，所提出的框架通过提供显式的中间推理指导，提高了ICL的性能。
英文摘要：
Recent advances in large language models (LLMs) have shown that Chain-of-Thought (CoT) reasoning can substantially improve performance on complex reasoning tasks. At the same time, In-Context Learning (ICL) has become an important mechanism for adapting LLMs to new tasks without updating model parameters, using only examples provided in the prompt. However, standard ICL often struggles on tasks that require multi-step reasoning, because the demonstrations usually contain only input-output pairs and lack explicit intermediate reasoning steps. This paper introduces an Automatic Chain-of-Thought (Auto-CoT) framework to improve ICL by automatically constructing reasoning-enhanced demonstrations. Auto-CoT generates reasoning chains for input-output examples, augments the prompt context with structured intermediate explanations, and removes irrelevant or low-quality demonstrations through a systematic selection process. By incorporating high-quality reasoning examples into the ICL prompt, Auto-CoT guides the model toward more reliable reasoning and improves prediction accuracy. Experiments across multiple reasoning tasks demonstrate that the proposed framework improves ICL performance by providing explicit intermediate reasoning guidance.
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。
