arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01403cs.AIcs.LO
收藏

通过简短公式的可解释性:命题逻辑与实现的情况

Explainability via Short Formulas: the Case of Propositional Logic with Implementation

Tampere University(坦佩雷大学)

Reijo Jaakkola, Tomi Janhunen, Antti Kuusisto, Masood Feyzbakhsh Rankooh, Miikka Vilander

摘要:

我们概念化的逻辑和公式大小的可解释性,给出了一些相关的定义,在一个非常一般的设置的可解释性。我们的主要兴趣是所谓的特殊解释问题,其目的是解释输入模型中输入公式的真值。解释是最小尺寸的公式,其(1)与输入模型上的输入公式一致,并且(2)将所涉及的真值全局地传输到输入公式,即,在每一个模型。作为一个重要的例子,我们研究命题逻辑在这种情况下,并表明,特殊的可解释性问题是完整的第二层次的多项式。我们还提供了一个实现这个问题的答案集编程和调查的能力,解释答案的n-皇后和支配集问题。

英文摘要:

We conceptualize explainability in terms of logic and formula size, giving a number of related definitions of explainability in a very general setting. Our main interest is the so-called special explanation problem which aims to explain the truth value of an input formula in an input model. The explanation is a formula of minimal size that (1) agrees with the input formula on the input model and (2) transmits the involved truth value to the input formula globally, i.e., on every model. As an important example case, we study propositional logic in this setting and show that the special explainability problem is complete for the second level of the polynomial hierarchy. We also provide an implementation of this problem in answer set programming and investigate its capacity in relation to explaining answers to the n-queens and dominating set problems.

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。

↑