Integrating attention into explanation frameworks for language and vision transformers
By: Marte Eggen, Jacob Lysnæs-Larsen, Inga Strümke
Potential Business Impact:
Shows how computers understand things by looking at what's important.
The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a growing interest in attention-based model explanations. Although attention weights do not directly determine model outputs, they reflect patterns of token influence that can inform and complement established explainability techniques. This work studies the potential of utilising the information encoded in attention weights to provide meaningful model explanations by integrating them into explainable AI (XAI) frameworks that target fundamentally different aspects of model behaviour. To this end, we develop two novel explanation methods applicable to both natural language processing and computer vision tasks. The first integrates attention weights into the Shapley value decomposition by redefining the characteristic function in terms of pairwise token interactions via attention weights, thus adapting this widely used game-theoretic solution concept to provide attention-driven attributions for local explanations. The second incorporates attention weights into token-level directional derivatives defined through concept activation vectors to measure concept sensitivity for global explanations. Our empirical evaluations on standard benchmarks and in a comparison study with widely used explanation methods show that attention weights can be meaningfully incorporated into the studied XAI frameworks, highlighting their value in enriching transformer explainability.
Similar Papers
User Perception of Attention Visualizations: Effects on Interpretability Across Evidence-Based Medical Documents
Computation and Language
Shows how computers understand medical papers.
There is More to Attention: Statistical Filtering Enhances Explanations in Vision Transformers
CV and Pattern Recognition
Shows how AI sees what's important.
Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
Computation and Language
Makes computer language models work better and simpler.