TY - DATA T1 - Analogy-based explanation evaluation dataset for HCOMP 2022 paper "It Is Like Finding a Polar Bear in the Savannah! Concept-level AI Explanations with Analogical Inference from Commonsense Knowledge." PY - 2025/02/06 AU - Gaole He AU - Agathe Balayn AU - Stefan Buijsman AU - Jie Yang AU - Ujwal Gadiraju UR - DO - 10.4121/de1df5c0-5430-40f9-ba9a-ba0d1f415f28.v1 KW - Human-centered Explainable AI KW - Analogy KW - Concept-level Explanation KW - Commonsense Knowledge N2 -

This repo contains all code and data associated with the paper "It Is Like Finding a Polar Bear in the Savannah! Concept-level AI Explanations with Analogical Inference from Commonsense Knowledge." The dataset mainly contains generated analogies and expert evaluations from five colleagues in TU Delft. Our experimental results indicate that the proposed qualitative dimensions can positively contribute to the perceived helpfulness of analogy-based explanations.

ER -