分解复杂问题的逐次逼近法
Successive Prompting for Decomposing Complex Questions
摘要：
处理需要做出潜在决策的复杂问题是一项具有挑战性的任务，特别是在监督有限的情况下。最近的作品利用大语言模型（LM）的能力，以执行复杂的问答在一个Few-Shot设置，演示如何输出中间合理化，同时解决复杂的问题，在一个单一的通行证。我们引入了“逐次迭代”，我们迭代地将复杂任务分解为简单任务，解决它，然后重复这个过程，直到我们得到最终的解决方案。连续提示将分解复杂问题的监督与回答简单问题的监督相结合，允许我们（1）在每个推理步骤中有多个机会查询上下文示例（2）学习与问答分开的问题分解，包括使用合成数据，以及（3）在大型LM表现不佳的情况下，使用定制（微调）组件进行推理步骤。中间监督通常是手动编写的，这可能是昂贵的收集。我们介绍了一种方法来生成一个合成数据集，可用于引导模型的分解和回答中间问题的能力。与具有相同监督的最先进模型相比，我们的最佳模型（具有连续提示）在DROP数据集的Few-Shot版本上实现了~5%的绝对F1的改进。
英文摘要：
Answering complex questions that require making latent decisions is a challenging task, especially when limited supervision is available. Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting by demonstrating how to output intermediate rationalizations while solving the complex question in a single pass. We introduce ``Successive Prompting'', where we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Successive prompting decouples the supervision for decomposing complex questions from the supervision for answering simple questions, allowing us to (1) have multiple opportunities to query in-context examples at each reasoning step (2) learn question decomposition separately from question answering, including using synthetic data, and (3) use bespoke (fine-tuned) components for reasoning steps where a large LM does not perform well. The intermediate supervision is typically manually written, which can be expensive to collect. We introduce a way to generate a synthetic dataset which can be used to bootstrap a model's ability to decompose and answer intermediate questions. Our best model (with successive prompting) achieves an improvement of ~5% absolute F1 on a few-shot version of the DROP dataset when compared with a state-of-the-art model with the same supervision.
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。
