Maieutic Prompting：基于递归解释的逻辑一致推理

来自今天的爱可可AI前沿推介

[CL] Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations

J Jung, L Qin, S Welleck...
 [University of Washington & Allen Institute for Artificial Intelligence]

Maieutic Prompting：基于递归解释的逻辑一致推理

简介：提出Maieutic Prompting，一种新的大型预训练语言模型推理方法，使模型能回答真/假问题并进行复杂推理。Maieutic Prompting系统地解析和评估了一棵具有递归性和逻辑关系的解释树，将推理表述为这些解释及其逻辑关系的可满足性问题。。结果显示，与目前的提示方法相比，准确率提高了20%，而且还能与有监督的模型竞争。Maieutic Prompting为推理提供了一个强大的、可解释的方法。

摘要：尽管大型预训练语言模型(LM)具有令人印象深刻的能力，但在进行一致推理时却很费劲；最近，提示语言模型产生自我指导推理的解释，已成为修正这一问题的一个有希望的方向。然而，这些方法从根本上受制于解释的正确性，而解释本身往往是含噪和不一致的。本文提出Maieutic Prompting，可以从含噪和不一致的几代语言模型中推断出一个问题的正确答案。Maieutic Prompting以归纳式(例如，X是真的，因为......)迭代地归纳出一棵解释树，然后将推理表述为这些解释及其逻辑关系的可满足性问题。在三个需要复杂常识推理的挑战性基准上测试了Maieutic Prompting的真/假QA。与最先进的提示方法相比，Maieutic Prompting实现了高达20%的准确率提升，并且作为一种完全无监督方法，其表现与有监督的模型具有竞争力。Maieutic Prompting在提供可解释的理由的同时还提高了推理的稳健性。

Despite their impressive capabilities, large pre-trained language models (LMs) struggle with consistent reasoning; recently, prompting LMs to generate explanations that self-guide the inference has emerged as a promising direction to amend this. However, these approaches are fundamentally bounded by the correctness of explanations, which themselves are often noisy and inconsistent. In this work, we develop Maieutic Prompting, which infers a correct answer to a question even from the noisy and inconsistent generations of LM. Maieutic Prompting induces a tree of explanations abductively (e.g. X is true, because ...) and recursively, then frames the inference as a satisfiability problem over these explanations and their logical relations. We test Maieutic Prompting for true/false QA on three challenging benchmarks that require complex commonsense reasoning. Maieutic Prompting achieves up to 20% better accuracy than state-of-the-art prompting methods, and as a fully unsupervised approach, performs competitively with supervised models. We also show that Maieutic Prompting improves robustness in inference while providing interpretable rationales.

论文链接：https://arxiv.org/abs/2205.11822