The paper introduces an influence score that measures how much each attention head contributes to classification decisions in Transformer models, specifically for prompt injection detection. The score blends directional effects on logits with structural impact within the residual stream, allowing analysis at head, layer, and network scales. When applied to a DeBERTa model, the framework uncovers different decision patterns for correct versus incorrect predictions, offering a balanced approach between detailed circuit analysis and global output methods.
arXiv:2604. 10098v2 Announce Type: replace Abstract: As the foundational architecture of modern machine learning, Transformers have driven remarkable progress across diverse AI domains.
arXiv:2605. 27458v2 Announce Type: replace-cross Abstract: Transformer has significantly propelled the development of artificial intelligence, and certainly the development of agents as well.
arXiv:2607. 12863v1 Announce Type: cross Abstract: Transformer language models are increasingly used as software components, yet biased outputs remain difficult to localize and repair inside the model.
Transformer language models are increasingly used as software components, yet biased outputs remain difficult to localize and repair inside the model. Existing fairness testing and repair methods largely operate at the input-output or retraining level, while recent work suggests that bias-related behavior can concentrate in a small set of attention heads.
arXiv:2509. 23806v2 Announce Type: replace-cross Abstract: Concolic testing for neural networks alternates concrete execution with constraint solving to search for inputs that flip model decisions.
arXiv:2607. 22367v1 Announce Type: new Abstract: Feature-attribution methods assign scores relating input variables to a model's output, but do not by themselves characterize how explicitly defined interaction operators compose across its intermediate layers.
The paper introduces an importance‑scoring metric for multi‑head transformer attention heads applied to tabular data, a domain where transformers have been less studied. Experiments on 40 diverse tabular datasets show that removing heads with the lowest importance scores has minimal impact on performance, while removing the most important head first causes the largest drop. The study finds that important heads are distributed across layers and vary significantly across different tabular schemas, suggesting that the proposed score can help reduce redundancy and improve transformer efficiency.
arXiv:2605.12952v2 Announce Type: replace Abstract: Grad-ECLIP is published at ICML 2024 and represents a new Transformer interpretation technical route (intermediate features-based). First, this pap...
The paper examines how to allocate attention heads and head dimensions across Transformer layers to balance expressivity and efficiency. It provides a mathematical analysis of early layers’ role in information extraction and characterizes the trade‑off between head count and dimension under a fixed parameter budget. The authors prove a saturation effect of softmax activations, showing that increasing head dimensions yields diminishing returns, especially for long sequences, and propose strategies for efficient parameter allocation across layers.
arXiv:2606. 29256v1 Announce Type: cross Abstract: In recent years, models based on the Transformer architecture have seen widespread applications and have become one of the core tools in the field of deep learning.
arXiv:2607. 02964v1 Announce Type: cross Abstract: A central goal of mechanistic interpretability is to understand how neural networks work and what each individual component does.
arXiv:2606. 26396v1 Announce Type: new Abstract: Pre-trained transformers have demonstrated remarkable generalization abilities, at times extending beyond the scope of their training data.