English
Related papers

Related papers: Patch-Effect Graph Kernels for LLM Interpretabilit…

200 papers

Graph-structured data plays a vital role in numerous domains, such as social networks, citation networks, commonsense reasoning graphs and knowledge graphs. While graph neural networks have been employed for graph processing, recent…

Computation and Language · Computer Science 2026-05-19 Wooyoung Kim , Byungyoon Park , Wooju Kim

Following their success across many domains, transformers have also proven effective for symbolic regression (SR); however, the internal mechanisms underlying their generation of mathematical operators remain largely unexplored. Although…

Machine Learning · Computer Science 2026-02-04 Arco van Breda , Erman Acar

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…

Machine Learning · Computer Science 2024-11-08 Jacob Dunefsky , Philippe Chlenski , Neel Nanda

This paper introduces a new framework for recovering causal graphs from observational data, leveraging the observation that the distribution of an effect, conditioned on its causes, remains invariant to changes in the prior distribution of…

Machine Learning · Computer Science 2026-02-04 Nang Hung Nguyen , Phi Le Nguyen , Thao Nguyen Truong , Trong Nghia Hoang , Masashi Sugiyama

Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…

Machine Learning · Computer Science 2024-07-30 Jorge García-Carrasco , Alejandro Maté , Juan Trujillo

We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior work consist of…

Machine Learning · Computer Science 2025-03-28 Samuel Marks , Can Rager , Eric J. Michaud , Yonatan Belinkov , David Bau , Aaron Mueller

Interpretable graph neural networks (XGNNs ) are widely adopted in various scientific applications involving graph-structured data. Existing XGNNs predominantly adopt the attention-based mechanism to learn edge or node importance for…

Machine Learning · Computer Science 2024-06-13 Yongqiang Chen , Yatao Bian , Bo Han , James Cheng

Neural networks have proven to be effective at solving machine learning tasks but it is unclear whether they learn any relevant causal relationships, while their black-box nature makes it difficult for modellers to understand and debug…

Machine Learning · Computer Science 2023-08-02 Fabrizio Russo , Francesca Toni

Graph auto-encoders have proved to be useful in network embedding task. However, current models only consider explicit structures and fail to explore the informative latent structures cohered in networks. To address this issue, we propose a…

Machine Learning · Computer Science 2021-10-01 Minglong Lei , Yong Shi , Lingfeng Niu

Large language models (LLMs) are being increasingly explored for graph tasks. Despite their remarkable success in text-based tasks, LLMs' capabilities in understanding explicit graph structures remain limited, particularly with large…

Machine Learning · Computer Science 2024-10-31 Sambhav Khurana , Xiner Li , Shurui Gui , Shuiwang Ji

The emergence of explainability methods has enabled a better comprehension of how deep neural networks operate through concepts that are easily understood and implemented by the end user. While most explainability methods have been designed…

Neurons and Cognition · Quantitative Biology 2022-03-17 Fernanda L. Ribeiro , Steffen Bollmann , Ross Cunnington , Alexander M. Puckett

Applying machine learning to molecules is challenging because of their natural representation as graphs rather than vectors.Several architectures have been recently proposed for deep learning from molecular graphs, but they suffer from…

Machine Learning · Statistics 2020-09-15 Jaak Simm , Adam Arany , Edward De Brouwer , Yves Moreau

Graph plays an important role in representing complex relationships in real-world applications such as social networks, biological data and citation networks. In recent years, Large Language Models (LLMs) have achieved tremendous success in…

Machine Learning · Computer Science 2024-03-19 Zheyuan Liu , Xiaoxin He , Yijun Tian , Nitesh V. Chawla

Graph neural networks (GNNs) are vulnerable to adversarial attacks, especially for topology perturbations, and many methods that improve the robustness of GNNs have received considerable attention. Recently, we have witnessed the…

Machine Learning · Computer Science 2024-12-25 Zhongjian Zhang , Xiao Wang , Huichi Zhou , Yue Yu , Mengmei Zhang , Cheng Yang , Chuan Shi

Graph Neural Networks (GNNs) have become a powerful tool for modeling and analyzing data with graph structures. The wide adoption in numerous applications underscores the value of these models. However, the complexity of these methods often…

Artificial Intelligence · Computer Science 2025-12-10 Tien Cuong Bui

Large language models ($\textbf{LLMs}$) have emerged as a powerful method for discovery. Instead of utilizing numerical data, LLMs utilize associated variable $\textit{semantic metadata}$ to predict variable relationships. Simultaneously,…

Machine Learning · Computer Science 2025-04-15 Alex Havrilla , David Alvarez-Melis , Nicolo Fusi

Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recovering these circuits typically requires a bespoke analytical pipeline for each new task.…

Machine Learning · Computer Science 2026-05-27 Barsat Khadka

Understanding the internal mechanisms of GPT-style transformers, particularly their capacity to perform in-context learning (ICL), is critical for advancing AI alignment and interpretability. In-context learning allows transformers to…

Machine Learning · Computer Science 2024-10-24 Samarth Bhargav , Alexander Gu

This article introduces PAGE, a parameterized generative interpretive framework. PAGE is capable of providing faithful explanations for any graph neural network without necessitating prior knowledge or internal details. Specifically, we…

Machine Learning · Computer Science 2024-09-09 Yang Qiu , Wei Liu , Jun Wang , Ruixuan Li

Motivated by interpretability and reliability, we investigate whether large language models (LLMs) deploy universal geometric structures to encode discrete, graph-structured knowledge. To this end, we present two complementary experimental…

Machine Learning · Computer Science 2025-11-25 David D. Baek , Yuxiao Li , Max Tegmark