paper-with-me

홈 › Papers

Evaluating self-attention interpretability through human-grounded experimental protocol

2023-03-27 · Milan Bhan, Nina Achache, Victor Legrand, Annabelle Blangero, Nicolas Chesneau

Attention mechanisms have played a crucial role in the development of complex architectures such as Transformers in natural language processing. However, Transformers remain hard to interpret and are considered as black-boxes. This paper aims to assess how attention coefficients from Transformers can help in providing interpretability. A new attention-based interpretability method called CLaSsification-Attention (CLS-A) is proposed. CLS-A computes an interpretability score for each word based on the attention coefficient distribution related to the part specific to the classification task within the Transformer architecture. A human-grounded experiment is conducted to evaluate and compare CLS-A to other interpretability methods. The experimental protocol relies on the capacity of an interpretability method to provide explanation in line with human reasoning. Experiment design includes measuring reaction times and correct response rates by human subjects. CLS-A performs comparably to usual interpretability methods regarding average participant reaction time and accuracy. The lower computational cost of CLS-A compared to other interpretability methods and its availability by design within the classifier make it particularly interesting. Data analysis also highlights the link between the probability score of a classifier prediction and adequate explanations. Finally, our work confirms the relevancy of the use of CLS-A and shows to which extent self-attention contains rich information to explain Transformer classifiers.

📄 PDF Abstract BibTeX arXiv:2303.15190

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

LAP: An Attention-Based Module for Concept Based Self-Interpretation and Knowledge Injection in Convolutional Neural Networks

2022-01-27 · Rassa Ghavami Modegh, Ahmad Salimi, Alireza Dizaji, Hamid R. Rabiee

Despite the state-of-the-art performance of deep convolutional neural networks, they are susceptible to bias and malfunction in unseen situations. Moreover, the complex computation behind their reasoning is not human-und…

Decision Makingvalid

Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging

2025-03-12 · Minjae Chung, Jong Bum Won, Ganghyun Kim, Yujin Kim 외

Although Vision Transformers (ViTs) have recently demonstrated superior performance in medical imaging problems, they face explainability issues similar to previous architectures such as convolutional neural networks. Re…

Decision MakingSelf-Supervised Learning

Interpretability in Activation Space Analysis of Transformers: A Focused Survey

2023-01-22 · Soniya Vijayakumar

The field of natural language processing has reached breakthroughs with the advent of transformers. They have remained state-of-the-art since then, and there also has been much research in analyzing, interpreting, and ev…

Survey

Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trust

2025-08-02 · Mohsen Abbaspour Onari, Lucie Charlotte Magister, Yaoxin Wu, Amalia Lupi 외 arxiv

Distal myopathy represents a genetically heterogeneous group of skeletal muscle disorders with broad clinical manifestations, posing diagnostic challenges in radiology. To address this, we propose a novel multimodal atte…

Medical Diagnosis

Affinity-based Attention in Self-supervised Transformers Predicts Dynamics of Object Grouping in Humans

2023-06-01 · Hossein Adeli, Seoyoung Ahn, Nikolaus Kriegeskorte, Gregory Zelinsky

The spreading of attention has been proposed as a mechanism for how humans group features to segment objects. However, such a mechanism has not yet been implemented and tested in naturalistic images. Here, we leverage th…

ObjectRepresentation Learning