cs.CLFeb 18, 2026

Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models

Authors: Melkamu Abay Mersha, Jugal Kalita

Organizations: College of Engineering and Applied Science, University of Colorado Colorado Springs, Colorado Springs, 80918, CO, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing explainability methods rely on final-layer attributions, capture either local token-level attributions or global attention patterns without unification, and lack context-awareness of inter-token dependencies and structural components. They also fail to capture how relevance evolves across layers and how structural components shape decision-making. To address these limitations, we proposed the Context-Aware Layer-wise Integrated Gradients (CA-LIG) Framework, a unified hierarchical attribution framework that computes layer-wise Integrated Gradients within each Transformer block and fuses these token-level attributions with class-specific attention gradients. This integration yields signed, context-sensitive attribution maps that capture supportive and opposing evidence while tracing the hierarchical flow of relevance through the Transformer layers. We evaluate the CA-LIG Framework across diverse tasks, domains, and transformer model families, including sentiment analysis and long and multi-class document classification with BERT, hate speech detection in a low-resource language setting with XLM-R and AfroLM, and image classification with Masked Autoencoder vision Transformer model. Across all tasks and architectures, CA-LIG provides more faithful attributions, shows stronger sensitivity to contextual dependencies, and produces clearer, more semantically coherent visualizations than established explainability methods. These results indicate that CA-LIG provides a more comprehensive, context-aware, and reliable explanation of Transformer decision-making, advancing both the practical interpretability and conceptual understanding of deep neural models.

Figures & tables

Figure 1: Proposed architecture of the Context-Aware Layer-wise Integrated Gradients (CA-LIG) framework.
Figure 2
Figure 3
Figure 7: Token-F1 scores on the Movie Reviews reasoning task. CA-LIG and CA-IG(last layer) achieve consistently higher performance than baseline methods.
Figure 8: Layer-wise sensitivity profiles for CA-LIG, classifier contribution, and mean attention to [CLS] . Transitional peaks at Layers 4 and 8 reflect key representational shifts. The final peak at Layer 12 corresponds to sentiment consolidation.
Figure 9: Qualitative comparison of explanations generated by baseline XAI methods and CA-LIG using a MAE model. Warmer colors denote regions with higher positive relevance, while cooler colors indicate lower relevance. Images are taken from the ASIRRA dataset [ 18 ] .
Figure 10: Example of an explanation generated using CA-LIG for a prediction made by MAE model. (a) Original input image, (b) CA-LIG explanation heatmap, (c) positively attributed regions, and (d) negatively attributed regions. Warmer colors indicate stronger relevance.
PerturbationClassGradCAM [ 61 ]LRP- ϵ\epsilon [ 9 ]LRP (Attn+Grad) [ 10 ]IG [ 70 ]Ours
Insertion ↑\uparrow Predicted0.4240.4480.5670.4730.617
Deletion ↓\downarrow Predicted0.3740.4370.2370.3460.215
Table 1: Perturbation-based AUC evaluation of explanation faithfulness. Higher insertion AUC (↑) indicates faster confidence recovery when important patches are added to a blurred baseline, while lower deletion AUC (↓) reflects faster confidence drop when critical patches are removed from the original image.
Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

AspectIG [ 70 ]Integrated Hessians [ 31 ]Transformer-LRP [ 10 ]CA-LIG Framework (Ours)
Core PrinciplePath-integrated gradients from baseline to inputSecond-order IG using Hessians for interaction effectsLRP/Deep Taylor rulesLayer-wise IG fused with class-specific attention gradients
Primary ObjectiveToken-level importance at input layer.Quantify pairwise feature interactions.Propagate and conserve relevance across attention and residuals.Produce hierarchical, context-aware token relevance across layers.
Derivative OrderFirst-orderSecond-orderRule-basedFirst-order IG with gradient-weighted attention integration
GranularityInput-level token salienceInteraction matrix between feature pairsSingle global input-level relevance mapPer-layer token attribution + fused contextual map + multi-layer rollout
Use of AttentionNoneNoneImplicit via LRP propagation rulesExplicit class-specific attention gradients .
Layer-wise TrackingNone (only final output layer)None (interaction-focused)Relevance flows through layersExplicit LIG at each layer to model relevance trajectories.
Appendix
Table 2: Methodological comparison of IG, Integrated Hessians, Transformer-LRP, and the proposed CA-LIG framework, highlighting how CA-LIG combines layer-wise Integrated Gradients with attention-gradient fusion to produce hierarchical, context-aware explanations.
Figure 12: CA-LIG token-level attributions for a positive IMDB review using BERT-Large. Brighter green indicates stronger positive evidence, red indicates negative relevance, and white denotes neutral tokens.
Figure 13: CA-LIG token-level attributions for a document labeled politics class from the 20 Newsgroups dataset using BERT-base. Brighter green tokens provide stronger positive evidence, lighter green indicates weaker support, red shows negative influence, and white denotes neutral relevance.
Figure 14: Token-level attribution visualization generated by the CA-LIG using the AfroLM model on an Amharic hate speech sample. Brighter Red tokens provide stronger negative evidence (hate); lighter red indicates weaker support; green shows positive influence; and white denotes neutral relevance. English translation: That religion is not respected, all its followers are destructive, and their behavior shows that they do not like peace anywhere.
Figure 15: Token-level attribution visualization generated by the CA-LIG using the XLM-R model on an Amharic hate speech sample. Brighter green tokens provide stronger positive evidence (not hate), lighter green indicates weaker support, red shows negative influence, and white denotes neutral relevance. English translation: It is important to believe in the rule of law. Anyone who breaks the law must be held accountable.
Figure 16: Example of a CA-LIG explanation for a prediction made by the MAE model on the CIFAR-10 dataset. (a) Original input image, (b) CA-LIG explanation heatmap, (c) positively attributed regions, and (d) negatively attributed regions. Warmer colors indicate stronger relevance to the model’s prediction. The CA-LIG explanation indicates that the MAE model’s predictions are driven by contextually related and semantically meaningful object parts. As illustrated in (b) and (c), strong positive relevance is consistently assigned to the head, torso, and lower body/feet. In contrast, (d) indicates negative relevance to background and peripheral regions that do not contribute to the prediction.
Figure 17: Qualitative comparison of explanations generated by various XAI methods using a Masked Autoencoder (MAE) fine-tuned on the CIFAR-10 dataset for image classification. Warmer colors denote regions with higher positive relevance to the predicted class, while cooler colors indicate lower relevance. Sample images are taken from the ASIRRA cat vs. dog dataset [ 18 ] .
Figure 18: Layer-wise token relevance visualization generated by our proposed CA-IG method using a BERT-base model fine-tuned on IMDB sentiment analysis. Brighter green indicates stronger positive evidence, red indicates negative relevance, and white denotes neutral tokens. The progression shows early layers distributing relevance across tokens, middle layers emphasizing sentiment-bearing words ( absolutely , amazing ), and deeper layers consolidating decision-relevant cues.
More in this topic

Transformer Interpretability

Transformer interpretability studies how attention, feed-forward layers, and hidden representations support model predictions and behavior.

See all 330 papers

Explore similar work

CardsList

  1. LIG: Layer-wise Integrated Gradients for Within-Layer Flow Analysis in Transformers

    Jun 19, 2026Eight Suzuki, Hideitsu Hino, Noboru MurataGradient-Based AttributionTransformer Interpretability

    Waseda University · Fujitsu Limited · The Institute of Statistical Mathematics

  2. Decision-Aware Attention Propagation for Vision Transformer Explainability

    Apr 20, 2026Sehyeong Jo, Gangjae Jang, Haesol ParkTransformer InterpretabilityVision Transformer

    Aarhus University · University of Colorado Boulder · KIST

  3. IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients

    Jun 29, 2026Duc Anh NguyenGradient-Based AttributionIntegrated Gradients

    Hanoi University of Science and Technology