流式批处理下的思维链提示:一项案例研究
Chain-Of-Thought Prompting Under Streaming Batch: A Case Study
AI总结:
针对现有自动 CoT 方法假设测试数据预先可见的局限,本文通过案例研究探索流式设置下利用批处理数据构建与优化思维链提示的方法。
摘要:
近来,大型语言模型(LLM)已展现出卓越能力。思维链(CoT)被提出作为协助 LLM 执行复杂推理的一种方式。然而,开发有效的提示可能是一项具有挑战性且耗费人力的任务。许多研究提出了从测试数据自动构建 CoT 的方法。它们大多假设所有测试数据在测试前均可见,并只选择一小部分子集来生成推理依据,这是一种不切实际的假设。本文提出一项案例研究,探讨如何在流式设置中利用批处理数据构建和优化思维链提示。
英文摘要:
Recently, Large Language Models (LLMs) have demonstrated remarkable capabilities. Chain-of-Thought (CoT) has been proposed as a way of assisting LLMs in performing complex reasoning. However, developing effective prompts can be a challenging and labor-intensive task. Many studies come out of some way to automatically construct CoT from test data. Most of them assume that all test data is visible before testing and only select a small subset to generate rationales, which is an unrealistic assumption. In this paper, we present a case study on how to construct and optimize chain-of-thought prompting using batch data in streaming settings.
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。