paper-with-me

홈 › Papers

DePass: Unified Feature Attributing by Simple Decomposed Forward Pass

2025-10-21 · Xiangyu Hong, Che Jiang, Kai Tian, Biqing Qi, Youbang Sun, Ning Ding, Bowen Zhou arxiv

Attributing the behavior of Transformer models to internal computations is a central challenge in mechanistic interpretability. We introduce DePass, a unified framework for feature attribution based on a single decomposed forward pass. DePass decomposes hidden states into customized additive components, then propagates them with attention scores and MLP's activations fixed. It achieves faithful, fine-grained attribution without requiring auxiliary training. We validate DePass across token-level, model component-level, and subspace-level attribution tasks, demonstrating its effectiveness and fidelity. Our experiments highlight its potential to attribute information flow between arbitrary components of a Transformer model. We hope DePass serves as a foundational tool for broader applications in interpretability.

📄 PDF Abstract BibTeX arXiv:2510.18462

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Decomposition Ascribed Synergistic Learning for Unified Image Restoration

2023-08-01 · Jinghao Zhang, Feng Zhao

Learning to restore multiple image degradations within a single model is quite beneficial for real-world applications. Nevertheless, existing works typically concentrate on regarding each degradation independently, while…

DeblurringDenoisingImage DeblurringImage Dehazing+6

Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making

2023-10-20 · Yanrui Du, Sendong Zhao, Haochun Wang, Yuhan Chen 외

Explaining black-box model behavior with natural language has achieved impressive results in various NLP tasks. Recent research has explored the utilization of subsequences from the input text as a rationale, providing u…

Decision Making

Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems

2023-05-20 · NeurIPS 2023 11 · Benjamin Coleman, Wang-Cheng Kang, Matthew Fahrbach, Ruoxi Wang 외

Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of m…

Recommendation Systems

A Characteristic Function for Shapley-Value-Based Attribution of Anomaly Scores

2020-04-09 · Naoya Takeishi, Yoshinobu Kawahara

In anomaly detection, the degree of irregularity is often summarized as a real-valued anomaly score. We address the problem of attributing such anomaly scores to input features for interpreting the results of anomaly det…

Anomaly DetectionSemi-supervised Anomaly DetectionSupervised Anomaly Detection

Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians

2019-01-24 · Vardan Papyan

We consider deep classifying neural networks. We expose a structure in the derivative of the logits with respect to the parameters of the model, which is used to explain the existence of outliers in the spectrum of the H…