Is Sparse Attention more Interpretable?

Is Sparse Attention more Interpretable?

2 June 2021

Isabelle Augenstein

Papers citing "Is Sparse Attention more Interpretable?"

12 / 12 papers shown

Title
Hierarchical Attention Network for Interpretable ECG-based Heart Disease Classification Mario Padilla Rodriguez Mohamed Nafea 28 0 0 25 Mar 2025
DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion Huiguo He Huan Yang Zixi Tuo Yuan Zhou Qiuyue Wang Yuhang Zhang Zeyu Liu Wenhao Huang Hongyang Chao Jian Yin DiffM VGen 62 12 0 17 Jul 2024
Sparse Autoencoders Find Highly Interpretable Features in Language Models Hoagy Cunningham Aidan Ewart Logan Riggs R. Huben Lee Sharkey MILM 33 344 0 15 Sep 2023
Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification Jiasheng Si Yingjie Zhu Deyu Zhou AAML 52 3 0 16 May 2023
Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning Jiasheng Si Yingjie Zhu Deyu Zhou 37 12 0 02 Dec 2022
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods Josip Jukić Martin Tutek Jan Snajder FAtt 24 0 0 15 Nov 2022
Exploring Self-Attention for Crop-type Classification Explainability Ivica Obadic R. Roscher Dario Augusto Borges Oliveira Xiao Xiang Zhu 30 7 0 24 Oct 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 111 35 0 15 Oct 2021
How Does Adversarial Fine-Tuning Benefit BERT? J. Ebrahimi Hao Yang Wei Zhang AAML 26 4 0 31 Aug 2021
Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training Shunsuke Kitada Hitoshi Iyatomi AAML 28 8 0 18 Apr 2021
e-SNLI: Natural Language Inference with Natural Language Explanations Oana-Maria Camburu Tim Rocktaschel Thomas Lukasiewicz Phil Blunsom LRM 287 622 0 04 Dec 2018
Towards A Rigorous Science of Interpretable Machine Learning Finale Doshi-Velez Been Kim XAI FaML 257 3,690 0 28 Feb 2017