SYNAPSE：无需重训的 Transformer 神经元分析与扰动框架

View PDF HTML (experimental)

Abstract:In recent years, Artificial Intelligence has become a powerful partner for complex tasks such as data analysis, prediction, and problem-solving, yet its lack of transparency raises concerns about its reliability. In sensitive domains such as healthcare or cybersecurity, ensuring transparency, trustworthiness, and robustness is essential, since the consequences of wrong decisions or successful attacks can be severe. To overcome these limitations, this work proposes SYNAPSE, a systematic, training-free framework (requiring no retraining of the base model) for understanding and stress-testing the internal behavior of Transformer models across domains. SYNAPSE extracts per-layer [CLS] representations, trains a lightweight linear probe to obtain global and per-class neuron rankings, and applies forward-hook interventions during inference. This design enables controlled, repeatable experiments on internal representations without altering the original model, thereby allowing weaknesses, stability patterns, and label-specific sensitivities to be measured and compared directly across tasks and architectures. SYNAPSE reveals a consistent organization of internal representations across the two evaluated domains, in which task-relevant information is encoded in broad, overlapping neuron subsets. This redundancy provides a strong degree of functional stability, while class-wise asymmetries expose heterogeneous specialization patterns and enable fine-grained, label-aware analysis. In contrast, small structured manipulations in weight or logit space are sufficient to redirect predictions, highlighting complementary vulnerability profiles and illustrating how SYNAPSE can guide the development of more robust and interpretable Transformer models.

Submission history

From: Enrique Tomás Martínez Beltrán [view email]
[v1] Mon, 9 Mar 2026 14:18:47 UTC (1,983 KB)
[v2] Tue, 20 Oct 2026 19:00:12 UTC (369 KB)