Evaluating the Faithfulness of Importance Measures in NLP by Recursively
Masking Allegedly Important Tokens and Retraining

Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining

15 October 2021

Vaibhav Adlakha

Siva Reddy

Papers citing "Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining"

10 / 10 papers shown

Title
From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models Zexing Xu Zhuang Luo Yichuan Li Kyumin Lee S. Rasoul Etesami 38 0 0 28 Jan 2025
F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI Xu Zheng Farhad Shirani Zhuomin Chen Chaohao Lin Wei Cheng Wenbo Guo Dongsheng Luo AAML 38 0 0 03 Oct 2024
Evaluating Saliency Explanations in NLP by Crowdsourcing Xiaotian Lu Jiyi Li Zhen Wan Xiaofeng Lin Koh Takeuchi Hisashi Kashima XAI FAtt LRM 27 1 0 17 May 2024
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods Josip Jukić Martin Tutek Jan Snajder FAtt 21 0 0 15 Nov 2022
Measuring the Mixing of Contextual Information in the Transformer Javier Ferrando Gerard I. Gállego Marta R. Costa-jussá 26 49 0 08 Mar 2022
Human Interpretation of Saliency-based Explanation Over Text Hendrik Schuff Alon Jacovi Heike Adel Yoav Goldberg Ngoc Thang Vu MILM XAI FAtt 144 39 0 27 Jan 2022
When less is more: Simplifying inputs aids neural network understanding R. Schirrmeister Rosanne Liu Sara Hooker T. Ball 24 5 0 14 Jan 2022
"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification Jasmijn Bastings Sebastian Ebert Polina Zablotskaia Anders Sandholm Katja Filippova 115 75 0 14 Nov 2021
A Framework for Learning to Request Rich and Contextually Useful Information from Humans Khanh Nguyen Yonatan Bisk Hal Daumé 47 16 0 14 Oct 2021
Towards A Rigorous Science of Interpretable Machine Learning Finale Doshi-Velez Been Kim XAI FaML 257 3,684 0 28 Feb 2017