Cover Image

Integrating attention into explanation frameworks for language and vision transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Eggen, Marte, Lysnæs-Larsen, Jacob, Strümke, Inga
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Probing the Probes: Methods and Metrics for Concept Alignment
by: Lysnæs-Larsen, Jacob, et al.
Published: (2025)

A transformer-based deep reinforcement learning approach to spatial navigation in a partially observable Morris Water Maze
by: Eggen, Marte, et al.
Published: (2024)

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
by: Eggen, Marte, et al.
Published: (2026)

A Framework for Causal Concept-based Model Explanations
by: Bjøru, Anna Rodum, et al.
Published: (2025)

Position: AI Security Policy Should Target Systems, Not Models
by: Riegler, Michael A., et al.
Published: (2026)

From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition
by: Pellano, Kimji N., et al.
Published: (2024)

Integrated electro-optic attention nonlinearities for transformers
by: Mickeler, Luis, et al.
Published: (2026)

From independent patches to coordinated attention: Controlling information flow in vision transformers
by: Murphy, Kieran A.
Published: (2026)

Choose Your Explanation: A Comparison of SHAP and GradCAM in Human Activity Recognition
by: Tempel, Felix, et al.
Published: (2024)

Easy attention: A simple attention mechanism for temporal predictions with transformers
by: Sanchis-Agudo, Marcial, et al.
Published: (2023)

Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral Palsy
by: Pellano, Kimji N., et al.
Published: (2024)

Comparison of different Unique hard attention transformer models by the formal languages they can recognize
by: Ryvkin, Leonid
Published: (2025)

Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?
by: Pu, Yingming, et al.
Published: (2024)

Enhancing compact convolutional transformers with super attention
by: Leandre, Simpenzwe Honore, et al.
Published: (2025)

On GNN explanability with activation rules
by: Veyrin-Forrer, Luca, et al.
Published: (2024)

The effect of whitening on explanation performance
by: Clark, Benedict, et al.
Published: (2026)

Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review
by: Lopez-Ramos, Luis M., et al.
Published: (2024)

Simple linear attention language models balance the recall-throughput tradeoff
by: Arora, Simran, et al.
Published: (2024)

Static and multivariate-temporal attentive fusion transformer for readmission risk prediction
by: Sun, Zhe, et al.
Published: (2024)

Mathematically rigorous proofs for Shapley explanations
by: van Batenburg, David
Published: (2025)

Evaluating SAE interpretability without explanations
by: Paulo, Gonçalo, et al.
Published: (2025)

A standard transformer and attention with linear biases for molecular conformer generation
by: Gurev, Viatcheslav, et al.
Published: (2025)

Critical attention scaling in long-context transformers
by: Chen, Shi, et al.
Published: (2025)

The explanation dialogues: an expert focus study to understand requirements towards explanations within the GDPR
by: State, Laura, et al.
Published: (2025)

Pi-transformer: A prior-informed dual-attention model for multivariate time-series anomaly detection
by: Maleki, Sepehr, et al.
Published: (2025)

Mechanistic interpretability for steering vision-language-action models
by: Häon, Bear, et al.
Published: (2025)

Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learning
by: Ziai, Amir, et al.
Published: (2024)

A multimodal slice discovery framework for systematic failure detection and explanation in medical image classification
by: Liu, Yixuan, et al.
Published: (2026)

Effector: A Python package for regional explanations
by: Gkolemis, Vasilis, et al.
Published: (2024)

Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting
by: Calleo, Yuri
Published: (2025)

QUEST: A robust attention formulation using query-modulated spherical attention
by: Govindarajan, Hariprasath, et al.
Published: (2026)

A path to natural language through tokenisation and transformers
by: Berman, David S., et al.
Published: (2026)

Learning spatially structured open quantum dynamics with regional-attention transformers
by: Du, Dounan, et al.
Published: (2025)

Linear attention is (maybe) all you need (to understand transformer optimization)
by: Ahn, Kwangjun, et al.
Published: (2023)

MCCE: Monte Carlo sampling of realistic counterfactual explanations
by: Redelmeier, Annabelle, et al.
Published: (2021)

Relational reasoning and inductive bias in transformers and large language models
by: Geerts, Jesse, et al.
Published: (2025)

MASCOTS: Model-Agnostic Symbolic COunterfactual explanations for Time Series
by: Płudowski, Dawid, et al.
Published: (2025)

Self-attention-based non-linear basis transformations for compact latent space modelling of dynamic optical fibre transmission matrices
by: Zheng, Yijie, et al.
Published: (2024)

Towards deployment-centric multimodal AI beyond vision and language
by: Liu, Xianyuan, et al.
Published: (2025)

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers
by: Grzywaczewski, Jakub, et al.
Published: (2026)