paper-with-me

홈 › Papers

QUACKIE: A NLP Classification Task With Ground Truth Explanations

2020-12-24 · Yves Rychener, Xavier Renard, Djamé Seddah, Pascal Frossard, Marcin Detyniecki

NLP Interpretability aims to increase trust in model predictions. This makes evaluating interpretability approaches a pressing issue. There are multiple datasets for evaluating NLP Interpretability, but their dependence on human provided ground truths raises questions about their unbiasedness. In this work, we take a different approach and formulate a specific classification task by diverting question-answering datasets. For this custom classification task, the interpretability ground-truth arises directly from the definition of the classification problem. We use this method to propose a benchmark and lay the groundwork for future research in NLP interpretability by evaluating a wide range of current state of the art methods.

📄 PDF Abstract BibTeX arXiv:2012.13190

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationQuestion Answering

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition

2023-05-29 · Xiaoliang Wu, Peter Bell, Ajitha Rajan

Explainable AI (XAI) techniques have been widely used to help explain and understand the output of deep learning models in fields such as image classification and Natural Language Processing. Interest in using XAI techni…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Deep LearningExplainable Artificial Intelligence (XAI)+5

Evaluating the Correctness of Explainable AI Algorithms for Classification

2021-05-20 · Orcun Yalcin, Xiuyi Fan, Siyuan Liu

Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysi…

Binary ClassificationClassificationExplainable Artificial Intelligence (XAI)Feature Importance

Evaluating Model Explanations without Ground Truth

2025-05-15 · Kaivalya Rawal, Zihao Fu, Eoin Delaney, Chris Russell

There can be many competing and contradictory explanations for a single model prediction, making it difficult to select which one to use. Current explanation evaluation frameworks measure quality by comparing against ide…

Feature ImportancemodelSensitivity

Evaluating Explainability for Graph Neural Networks

2022-08-19 · Chirag Agarwal, Owen Queen, Himabindu Lakkaraju, Marinka Zitnik

As post hoc explanations are increasingly used to understand the behavior of graph neural networks (GNNs), it becomes crucial to evaluate the quality and reliability of GNN explanations. However, assessing the quality of…

Provable concept learning for interpretable predictions using variational autoencoders

2022-04-01 · Armeen Taeb, Nicolo Ruggeri, Carina Schnuck, Fanny Yang

In safety-critical applications, practitioners are reluctant to trust neural networks when no interpretable explanations are available. Many attempts to provide such explanations revolve around pixel-based attributions o…

Variational Inference