"Will You Find These Shortcuts?" A Protocol for Evaluating the
Faithfulness of Input Salience Methods for Text Classification

"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification

14 November 2021

Jasmijn Bastings

Sebastian Ebert

Polina Zablotskaia

Anders Sandholm

Katja Filippova

Papers citing ""Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification"

14 / 14 papers shown

Title
Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification Leon Eshuijs Shihan Wang Antske Fokkens 26 0 0 09 May 2025
How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neurons Michael Pichat William Pogrund Armanush Gasparian Paloma Pichat Samuel Demarchi Michael Veillet-Guillem 42 3 0 26 Dec 2024
Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models Sepehr Kamahi Yadollah Yaghoobzadeh 37 0 0 21 Aug 2024
Accelerating the Global Aggregation of Local Explanations Alon Mor Yonatan Belinkov B. Kimelfeld FAtt 27 3 0 13 Dec 2023
Out-of-Distribution Generalization in Text Classification: Past, Present, and Future Linyi Yang Y. Song Xuan Ren Chenyang Lyu Yidong Wang Lingqiao Liu Jindong Wang Jennifer Foster Yue Zhang OOD 32 2 0 23 May 2023
Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Models Jean-Thomas Baillargeon Luc Lamontagne 27 1 0 16 Dec 2022
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods Josip Jukić Martin Tutek Jan Snajder FAtt 13 0 0 15 Nov 2022
Finding Dataset Shortcuts with Grammar Induction Dan Friedman Alexander Wettig Danqi Chen 25 14 0 20 Oct 2022
Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior Jean-Stanislas Denain Jacob Steinhardt AAML 31 7 0 27 Jun 2022
Measuring the Mixing of Contextual Information in the Transformer Javier Ferrando Gerard I. Gállego Marta R. Costa-jussá 21 48 0 08 Mar 2022
When less is more: Simplifying inputs aids neural network understanding R. Schirrmeister Rosanne Liu Sara Hooker T. Ball 21 5 0 14 Jan 2022
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining Andreas Madsen Nicholas Meade Vaibhav Adlakha Siva Reddy 96 35 0 15 Oct 2021
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets Mor Geva Yoav Goldberg Jonathan Berant 237 319 0 21 Aug 2019
Hypothesis Only Baselines in Natural Language Inference Adam Poliak Jason Naradowsky Aparajita Haldar Rachel Rudinger Benjamin Van Durme 190 576 0 02 May 2018