Search Results for author:
Found 12 papers, 3 papers with code
Towards Attributions of Input Variables in a Coalition
This paper aims to develop a new attribution method to explain the conflict between individual variables' attributions and their coalition's attribution from a fully new perspective.
Mitigating Shortcuts in Language Models with Soft Label Encoding
Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks.
Natural Language Understanding
Out-of-Distribution Generalization
Explainability for Large Language Models: A Survey
For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge.
Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions
Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the final output.
Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts
In this paper, we focus on mean-field variational Bayesian Neural Networks (BNNs) and explore the representation capacity of such BNNs by investigating which types of concepts are less likely to be encoded by the BNN.
Concept-Level Explanation for the Generalization of a DNN
Therefore, in this paper, we investigate the generalization power of each interactive concept, and we use the generalization power of different interactive concepts to explain the generalization power of the entire DNN.
Trap of Feature Diversity in the Learning of MLPs
In this paper, we focus on a typical two-phase phenomenon in the learning of multi-layer perceptrons (MLPs), and we aim to explain the reason for the decrease of feature diversity in the first phase.
Discovering and Explaining the Representation Bottleneck of DNNs
This paper explores the bottleneck of feature representations of deep neural networks (DNNs), from the perspective of the complexity of interactions between input variables encoded in DNNs.
Defining and Quantifying the Emergence of Sparse Concepts in DNNs
This paper aims to illustrate the concept-emerging phenomenon in a trained DNN.
A General Taylor Framework for Unifying and Revisiting Attribution Methods
However, the attribution problem has not been well-defined, which lacks a unified guideline to the contribution assignment process.
Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution
The basic idea is to learn a source signal by back-propagation such that the mutual information between input and output should be as much as possible preserved in the mutual information between input and the source signal.
A Unified Taylor Framework for Revisiting Attribution Methods
Attribution methods have been developed to understand the decision-making process of machine learning models, especially deep neural networks, by assigning importance scores to individual features.
