ResearchTrend.AI
Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers

Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers

Tobias Leemann
Alina Fastowski
Felix Pfeiffer
Gjergji Kasneci
ArXivPDFHTML

Papers citing "Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers"

6 / 6 papers shown
Title
Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
Mahdi Dhaini
Ege Erdogan
Nils Feldhus
Gjergji Kasneci
34
0
0
02 May 2025
Large Language Models as Attribution Regularizers for Efficient Model Training
Large Language Models as Attribution Regularizers for Efficient Model Training
Davor Vukadin
Marin Šilić
Goran Delač
36
0
0
27 Feb 2025
The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI
The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI
Miriam Schirmer
Tobias Leemann
Gjergji Kasneci
Jürgen Pfeffer
David Jurgens
67
0
0
12 Aug 2024
ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports
ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports
Katharina Jeblick
B. Schachtner
Jakob Dexl
Andreas Mittermeier
Anna Theresa Stüber
...
Tobias Weber
Philipp Wesp
B. Sabel
J. Ricke
Michael Ingrisch
LM&MA
MedIm
100
368
0
30 Dec 2022
From Shapley Values to Generalized Additive Models and back
From Shapley Values to Generalized Additive Models and back
Sebastian Bordt
U. V. Luxburg
FAtt
TDI
51
33
0
08 Sep 2022
Neural Legal Judgment Prediction in English
Neural Legal Judgment Prediction in English
Ilias Chalkidis
Ion Androutsopoulos
Nikolaos Aletras
AILaw
ELM
98
279
0
05 Jun 2019