arXiv Machine Learning July 9, 2026 By Lasse Marten Jantsch, Dong-Jae Koh, Seonghyeon Lee, Young-Kyoon Suh

Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation

Read the original on arXiv Machine Learning →

arXiv:2603. 19742v2 Announce Type: replace Abstract: Understanding the internal mechanisms of transformer-based large language models (LLMs) is crucial for their reliable deployment and effective operation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computation and Language

6d ago

Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation

arXiv:2603.19742v3 Announce Type: replace-cross Abstract: Understanding the internal mechanisms of transformer-based large language models (LLMs) is crucial for their reliable deployment and effectiv...

By Lasse Marten Jantsch, Dong-Jae Koh, Seonghyeon Lee, Young-Kyoon Suh

llms benchmarks safety

arXiv AI

Sep 16

ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers

The paper introduces ResLRP, an extension of Layer-wise Relevance Propagation that explicitly handles residual connections in Vision Transformers to prevent attribution explosion. It demonstrates that residual cancellation causes instability in ViT explanations, and that ResLRP improves faithfulness and localization across a wide range of ViT architectures, including Vision Language Models. The method also provides a diagnostic measure for predicting attribution degradation and successfully localizes Sparse Autoencoder features.

By Jim Berend, Reduan Achtibat, Daniel Sch\"affer, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer

llms multimodal benchmarks

arXiv AI

Jun 9

ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding

arXiv:2606. 07524v1 Announce Type: cross Abstract: The explosive growth of large language models (LLMs) has created a heterogeneous and poorly documented ecosystem, making systematic model comparison increasingly important for provenance auditing, security analysis, and model selection.

By Zirui Wang, Yusen Hou, Shaofeng Liang, Bowen Tian, Yanlin Zhang, Wenshuo Chen, Yutao Yue

llms rag nlp benchmarks safety

arXiv AI

Jul 7

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

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.

By Arnau Marin-Llobet, Stefan Heimersheim

llms safety

arXiv Machine Learning

Jul 22

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs

arXiv:2603. 21014v2 Announce Type: replace Abstract: Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information.

By Florent Draye, Vedant Palit, Abir Harrasse, Tung-Yu Wu, Jiarui Liu, Punya Syon Pandey, Roderick Wu, Chih-Hao Hsu, Terry Jingchen Zhang, Zhijing Jin, Bernhard Sch\"olkopf

llms safety

arXiv Machine Learning

Sep 10

LLM Layers Immediately Correct Each Other

arXiv:2609.07876v1 Announce Type: cross Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linea...

By Arjun Patrawala, Jiahai Feng, Erik Jones, Jacob Steinhardt

llms safety

One email a morning, machine-written

Related stories

Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation

ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers

ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs

LLM Layers Immediately Correct Each Other