Weight Patching: Toward Source-Level Mechanistic Localization in LLMs

• URL: http://arxiv.org/abs/2604.13694v1
• Date: Wed, 15 Apr 2026 10:21:38 GMT
• Title: Weight Patching: Toward Source-Level Mechanistic Localization in LLMs
• Abstract summary: We propose Weight Patching, a parameter-space intervention method for source-oriented analysis in paired same-architecture models.<n>We introduce a framework centered on a vector-anchor behavioral interface that provides a shared internal criterion for whether a task-relevant control state has been formed.
• Score: 12.558998651017374
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mechanistic interpretability seeks to localize model behavior to the internal components that causally realize it. Prior work has advanced activation-space localization and causal tracing, but modules that appear important in activation space may merely aggregate or amplify upstream signals rather than encode the target capability in their own parameters. To address this gap, we propose Weight Patching, a parameter-space intervention method for source-oriented analysis in paired same-architecture models that differ in how strongly they express a target capability under the inputs of interest. Given a base model and a behavior-specialized counterpart, Weight Patching replaces selected module weights from the specialized model into the base model under a fixed input. We instantiate the method on instruction following and introduce a framework centered on a vector-anchor behavioral interface that provides a shared internal criterion for whether a task-relevant control state has been formed or recovered in open-ended generation. Under this framework, the analysis reveals a hierarchy from shallow candidate source-side carriers to aggregation and routing modules, and further to downstream execution circuits. The recovered component scores can also guide mechanism-aware model merging, improving selective fusion across the evaluated expert combinations and providing additional external validation.

Related papers

• Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms [6.233211865365017]
  Circuit analysis is a central approach in mechanistic interpretability, but it is typically target-conditioned.<n>We introduce distribution-level unsupervised feature discovery.<n>Across clustering and steering analyses, the discovered clusters expose continuation modes that single-view baselines miss.
  arXiv  Detail & Related papers  (2026-06-06T15:46:54Z)
• Dissecting Jet-Tagger Through Mechanistic Interpretability [0.0]
  We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained on the Top Quark Tagging reference dataset.<n>We identify the computational circuit responsible for jet classification and characterizing the physical content of its internal representations.
  arXiv  Detail & Related papers  (2026-05-11T02:11:47Z)
• ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding [23.27523995613204]
  We propose ABLE (Attribution-Based Large-model Embedding), a framework that leverages the interpretability space to construct model representations.<n>By aggregating gradient-based feature attributions via a tokenizer-agnostic word-level alignment, ABLE captures model-specific input-sensitivity patterns.<n>Our training-free approach achieves competitive or superior performance in relation prediction, model routing, and benchmark score prediction.
  arXiv  Detail & Related papers  (2026-04-20T04:55:11Z)
• Source-Free Object Detection with Detection Transformer [59.33653163035064]
  Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data.<n>Most existing SFOD approaches are either confined to conventional object detection (OD) models like Faster R-CNN or designed as general solutions without tailored adaptations for novel OD architectures, especially Detection Transformer (DETR)<n>In this paper, we introduce Feature Reweighting ANd Contrastive Learning NetworK (FRANCK), a novel SFOD framework specifically designed to perform query-centric feature enhancement for DETRs.
  arXiv  Detail & Related papers  (2025-10-13T07:35:04Z)
• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings [9.48243749038739]
  Local Interpretable Model-Agnostic Explanations (LIME) have advanced the interpretability of black-box machine learning models.<n>LIME's inherent randomness in perturbation and sampling can lead to locality and instability issues.<n>We propose a novel Instance-based Transfer Learning LIME framework (ITL-LIME) that enhances explanation fidelity and stability in data-constrained environments.
  arXiv  Detail & Related papers  (2025-08-19T09:18:20Z)
• REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering [26.428347164111926]
  Inference-time steering aims to alter a large language model's responses without changing its parameters.<n>Existing approaches often rely on simplistic cues or ad hoc generalizations.<n>We introduce REAL, a framework for identifying behavior-relevant modules in Transformer models.
  arXiv  Detail & Related papers  (2025-06-10T02:16:50Z)
• OSM: Leveraging Model Checking for Observing Dynamic 1 behaviors in Aspect-Oriented Applications [0.0]
  observe-based statistical model-checking (OSM) framework devised to craft executable formal models directly from foundational system code. This ensures the unyielding performance of electronic health record systems amidst shifting preconditions.
  arXiv  Detail & Related papers  (2024-03-03T00:03:34Z)
• Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking [53.66999416757543]
  We study how fine-tuning affects the internal mechanisms implemented in language models. Fine-tuning enhances, rather than alters, the mechanistic operation of the model.
  arXiv  Detail & Related papers  (2024-02-22T18:59:24Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)
• Transforming Feature Space to Interpret Machine Learning Models [91.62936410696409]
  This contribution proposes a novel approach that interprets machine-learning models through the lens of feature space transformations. It can be used to enhance unconditional as well as conditional post-hoc diagnostic tools. A case study on remote-sensing landcover classification with 46 features is used to demonstrate the potential of the proposed approach.
  arXiv  Detail & Related papers  (2021-04-09T10:48:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.