ResearchTrend.AI
Discretized Integrated Gradients for Explaining Language Models

Discretized Integrated Gradients for Explaining Language Models

Soumya Sanyal
Xiang Ren
    FAtt
ArXivPDFHTML

Papers citing "Discretized Integrated Gradients for Explaining Language Models"

7 / 7 papers shown
Title
Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models
Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models
Sepehr Kamahi
Yadollah Yaghoobzadeh
64
0
0
21 Aug 2024
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Victor Sanh
Lysandre Debut
Julien Chaumond
Thomas Wolf
98
7,386
0
02 Oct 2019
Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
W. James Murdoch
Peter J. Liu
Bin Yu
45
209
0
16 Jan 2018
Learning Important Features Through Propagating Activation Differences
Learning Important Features Through Propagating Activation Differences
Avanti Shrikumar
Peyton Greenside
A. Kundaje
FAtt
85
3,848
0
10 Apr 2017
Axiomatic Attribution for Deep Networks
Axiomatic Attribution for Deep Networks
Mukund Sundararajan
Ankur Taly
Qiqi Yan
OOD
FAtt
79
5,920
0
04 Mar 2017
Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
Avanti Shrikumar
Peyton Greenside
A. Shcherbina
A. Kundaje
FAtt
42
782
0
05 May 2016
Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers
Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers
Alexander Binder
G. Montavon
Sebastian Lapuschkin
K. Müller
Wojciech Samek
FAtt
44
456
0
04 Apr 2016