使用持久记忆丰富模型的信念概念
Enriching a Model's Notion of Belief using a Persistent Memory
摘要:
虽然预训练的语言模型(PTLM)已被证明包含大量的世界知识,但即使在使用专门的训练技术来减少不一致性之后,它们仍然可以在探测时产生不一致的问题答案。因此,很难确定模型实际上“相信”这个世界。我们的目标是减少这个问题,使系统在全球范围内更加一致和准确。我们的方法是添加一个记忆组件--一个BeliefBank --记录模型的答案,以及两个使用它来提高信念一致性的机制。首先,一个推理组件--加权SAT求解器--通过翻转与其他答案明显冲突的答案来提高一致性。其次,反馈组件重新查询模型,但使用已知的信念作为上下文。我们表明,在一个受控的实验设置,这两种机制提高了准确性和一致性。这是重要的,因为这是赋予模型不断发展的记忆的第一步,使它们能够构建一个更连贯的世界图景。
英文摘要:
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.
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。