Although pretrained language models (PTLMs) have been shown to contain significant amounts of world knowledge, they can still produce inconsistent answers to questions when probed, even after using specialized training techniques to reduce inconsistency. As a result, it can be hard to identify what the model actually "believes" about the world. Our goal is to reduce this problem, so systems are more globally consistent and accurate in their answers. Our approach is to add a memory component - a BeliefBank - that records a model's answers, and two mechanisms that use it to improve consistency among beliefs. First, a reasoning component - a weighted SAT solver - improves consistency by flipping answers that significantly clash with others. Second, a feedback component re-queries the model but using known beliefs as context. We show that, in a controlled experimental setting, these two mechanisms improve both accuracy and consistency. This is significant as it is a first step towards endowing models with an evolving memory, allowing them to construct a more coherent picture of the world.
翻译:尽管经过事先训练的语言模型(PTLMS)已经证明含有大量的世界知识,但它们仍然能够对被调查的问题提供不一致的答案,即使使用了专门的培训技术来减少不一致的情况。 因此,很难确定该模型实际上什么是世界的“信仰 ” 。 我们的目标是减少这个问题, 使系统在答案上更加全球一致和准确。 我们的方法是添加一个记忆部分 — — 信仰银行 — — 记录模型的答案,以及两个机制,用它来提高信仰的一致性。 首先,一个推理部分 — — 加权SAT求解器 — — 通过翻转与其他人大相矛盾的答案来提高一致性。 其次,反馈部分重新检查模型,但用已知的信念作为背景。 我们表明,在受控的实验环境中,这两种机制既能提高准确性和一致性,又能提高一致性。 这很重要,因为它是朝着以不断演变的记忆来赋予模型以更一致的模型迈出的第一步,使其能够构建出更加一致的世界景象。