paper-with-me

홈 › Papers

On the stability, correctness and plausibility of visual explanation methods based on feature importance

2023-10-25 · Romain Xu-Darme, Jenny Benois-Pineau, Romain Giot, Georges Quénot, Zakaria Chihani, Marie-Christine Rousset, Alexey Zhukov

In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w.r.t. a set of desired properties. In this work, we study the articulation between the stability, correctness and plausibility of explanations based on feature importance for image classifiers. We show that the existing metrics for evaluating these properties do not always agree, raising the issue of what constitutes a good evaluation metric for explanations. Finally, in the particular case of stability and correctness, we show the possible limitations of some evaluation metrics and propose new ones that take into account the local behaviour of the model under test.

📄 PDF Abstract BibTeX arXiv:2311.12860

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Importance

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers

2022-05-01 · ACL 2022 5 · Bugeun Kim, Kyung Seo Ki, Sangkyu Rhim, Gahgene Gweon

In this paper, we propose a neural model EPT-X (Expression-Pointer Transformer with Explanations), which utilizes natural language explanations to solve an algebraic word problem. To enhance the explainability of the enc…

MathMath Word Problem Solving

An Experimental Study on Generating Plausible Textual Explanations for Video Summarization

2025-09-30 · Thomas Eleftheriadis, Evlampios Apostolidis, Vasileios Mezaris arxiv

In this paper, we present our experimental study on generating plausible textual explanations for the outcomes of video summarization. For the needs of this study, we extend an existing framework for multigranular explan…

Video Summarization

Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding

2026-03-26 · Gregor Baer, Chao Zhang, Isel Grau, Pieter Van Gorp arxiv

Explainable AI (XAI) methods are commonly evaluated with functional metrics such as correctness, which computationally estimate how accurately an explanation reflects the model's reasoning. Higher correctness is assumed …

Time Series Classification

Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models

2024-02-07 · Chirag Agarwal, Sree Harsha Tanneru, Himabindu Lakkaraju

Large Language Models (LLMs) are deployed as powerful tools for several natural language processing (NLP) applications. Recent works show that modern LLMs can generate self-explanations (SEs), which elicit their intermed…

Decision Making

VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives

2022-06-22 · Zhuofan Ying, Peter Hase, Mohit Bansal

Many past works aim to improve visual reasoning in models by supervising feature importance (estimated by model explanation techniques) with human annotations such as highlights of important image regions. However, recen…

Feature ImportanceQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)+1