paper-with-me

홈 › Papers

On the (In)fidelity and Sensitivity of Explanations

2019-12-01 · NeurIPS 2019 12 · Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Suggala, David I. Inouye, Pradeep K. Ravikumar

We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidelity, and sensitivity. We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods. By varying the perturbation distribution that defines infidelity, we obtain novel explanations by optimizing infidelity, which we show to out-perform existing explanations in both quantitative and qualitative measurements. Another salient question given these measures is how to modify any given explanation to have better values with respect to these measures. We propose a simple modification based on lowering sensitivity, and moreover show that when done appropriately, we could simultaneously improve both sensitivity as well as fidelity.

📄 PDF Abstract BibTeX

Code (1)

chihkuanyeh/saliency_evaluation 공식 구현 pytorch

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

On the (In)fidelity and Sensitivity for Explanations

2019-01-27 · Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Sai Suggala, David I. Inouye 외

We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidel…

Sensitivity

Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets

2023-11-03 · M. Miró-Nicolau, A. Jaume-i-Capó, G. Moyà-Alcover

The evaluation of the fidelity of eXplainable Artificial Intelligence (XAI) methods to their underlying models is a challenging task, primarily due to the absence of a ground truth for explanations. However, assessing fi…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)

GLIME: General, Stable and Local LIME Explanation

2023-11-27 · NeurIPS 2023 11 · Zeren Tan, Yang Tian, Jian Li

As black-box machine learning models grow in complexity and find applications in high-stakes scenarios, it is imperative to provide explanations for their predictions. Although Local Interpretable Model-agnostic Explanat…

Investigating sanity checks for saliency maps with image and text classification

2021-06-08 · Narine Kokhlikyan, Vivek Miglani, Bilal Alsallakh, Miguel Martin 외

Saliency maps have shown to be both useful and misleading for explaining model predictions especially in the context of images. In this paper, we perform sanity checks for text modality and show that the conclusions made…

text-classificationText Classification

FaithLM: Towards Faithful Explanations for Large Language Models

2024-02-07 · Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang 외

Large Language Models (LLMs) have become proficient in addressing complex tasks by leveraging their extensive internal knowledge and reasoning capabilities. However, the black-box nature of these models complicates the t…

Decision Making