concept-based-xai

Tag

Cards List
#concept-based-xai

ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI

arXiv cs.AI · 2026-07-13 Cached

ConceptSMILE is a perturbation-based auditing framework for evaluating the reliability of concept-based explainable AI, tested on retinal fundus images.

0 favorites 0 likes
#concept-based-xai

Low-cost concept-based localized explanations: How far can we get with training-free approaches?

arXiv cs.AI · 2026-06-30 Cached

This paper evaluates the zero-shot capability of multimodal large language models (MLLMs) for localized concept naming in images, proposing a reproducible evaluation protocol that achieves 62-88% object-level accuracy without training.

0 favorites 0 likes
← Back to home

Submit Feedback