paper-with-me

홈 › Papers

Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge

2022-09-27 · Cara Widmer, Md Kamruzzaman Sarker, Srikanth Nadella, Joshua Fiechter, Ion Juvina, Brandon Minnery, Pascal Hitzler, Joshua Schwartz, Michael Raymer

Concept induction, which is based on formal logical reasoning over description logics, has been used in ontology engineering in order to create ontology (TBox) axioms from the base data (ABox) graph. In this paper, we show that it can also be used to explain data differentials, for example in the context of Explainable AI (XAI), and we show that it can in fact be done in a way that is meaningful to a human observer. Our approach utilizes a large class hierarchy, curated from the Wikipedia category hierarchy, as background knowledge.

📄 PDF Abstract BibTeX arXiv:2209.13710

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable Artificial Intelligence (XAI)Logical Reasoning

Methods 이 논문이 사용한 방법론

Ontology 설명 없음
BASE 설명 없음

Similar Papers 제목 키워드 기반

Gender Segregation: Analysis across Sectoral-Dominance in the UK Labour Market

2023-03-08 · Riccardo Leoncini, Mariele Macaluso, Annalivia Polselli

This paper aims to evaluate how changing patterns of sectoral gender segregation play a role in accounting for women's employment contracts and wages in the UK between 2005 and 2020. We then study wage differentials in g…

Diversity and Inclusion Metrics in Subset Selection

2020-02-09 · Margaret Mitchell, Dylan Baker, Nyalleng Moorosi, Emily Denton 외

The ethical concept of fairness has recently been applied in machine learning (ML) settings to describe a wide range of constraints and objectives. When considering the relevance of ethical concepts to subset selection p…

DiversityFairness

Interpretability of Language Models via Task Spaces

2024-06-10 · Lucas Weber, Jaap Jumelet, Elia Bruni, Dieuwke Hupkes

The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes. In this paper, we present an alternative approach, concentrating on t…

Are Shortest Rationales the Best Explanations for Human Understanding?

2022-03-16 · ACL 2022 5 · Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao 'Kenneth' Huang

Existing self-explaining models typically favor extracting the shortest possible rationales - snippets of an input text "responsible for" corresponding output - to explain the model prediction, with the assumption that s…

Interactive Naming for Explaining Deep Neural Networks: A Formative Study

2018-12-18 · Mandana Hamidi-Haines, Zhongang Qi, Alan Fern, Fuxin Li 외

We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classifi…

General Classification