Evaluating Feature Attribution Methods: an Usecase on a Neural Fact-checking Model

Evaluating Feature Attribution Methods: an Usecase on a Neural Fact-checking Model

Simons, Annabel (TU Delft Electrical Engineering, Mathematics and Computer Science)

Anand, A. (mentor)
Lyu, L. (mentor)
Corti, L. (mentor)
Loog, M. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2023-02-03

In today's society, claims are everywhere, in the online and offline world. Fact-checking models can check these claims and predict if a claim is true or false, but how can these models be checked? Post-hoc XAI feature attribution methods can be used for this. These methods give scores indicating the influence of the individual tokens on the model's decision-making. In our research, we evaluate three popular feature attribution methods in the context of fact-checking: LIME, Kernel SHAP, and Integrated Gradients. We used the NLP architecture ExPred as a fact-checking model in our research. The feature attribution methods were evaluated using a human-grounded and pseudo ground truth evaluation. The results from these evaluations indicate that Integrated Gradients enables humans to form an opinion better and performs better in our pseudo ground truth evaluation. A potential explanation is that the iterations should be increased for LIME and Kernel SHAP. Our findings suggest that Integrated Gradients performs better in our study. Still, more research for other tasks and models would be beneficial to ensure that these results apply to other cases.

XAI
Explainable Artificial Intelligence
Comparison
Fact-checking
Feature Attribution Methods
Neural Network

http://resolver.tudelft.nl/uuid:ccc39e3a-f233-4279-a230-dbc33ce4147e

https://github.com/Herbje/Evaluating-Feature-Attribution-Methods Repository link GitHub

Student theses

bachelor thesis

© 2023 Annabel Simons