English
Related papers

Related papers: N2G: A Scalable Approach for Quantifying Interpret…

200 papers

Although deep neural networks have shown well-performance in various tasks, the poor interpretability of the models is always criticized. In the paper, we propose a new interpretable neural network method, by embedding neurons into the…

Machine Learning · Computer Science 2022-11-16 Wei Han , Yangqiming Wang , Christian Böhm , Junming Shao

While Large Language Models (LLMs) have shown exceptional generalization capabilities, their ability to process graph data, such as molecular structures, remains limited. To bridge this gap, this paper proposes Graph2Token, an efficient…

Machine Learning · Computer Science 2025-03-11 Runze Wang , Mingqi Yang , Yanming Shen

Large Language Models (LLMs) typically have billions of parameters and are thus often difficult to interpret in their operation. In this work, we demonstrate that it is possible to decode neuron weights directly into token probabilities…

Computation and Language · Computer Science 2025-03-03 Harry J Davies

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Computation and Language · Computer Science 2026-05-05 Or Shafran , Atticus Geiger , Mor Geva

Interpreting complex neural networks is crucial for understanding their decision-making processes, particularly in applications where transparency and accountability are essential. This proposed method addresses this need by focusing on…

Neural and Evolutionary Computing · Computer Science 2024-12-10 Deepshikha Bhati , Fnu Neha , Md Amiruzzaman , Angela Guercio , Deepak Kumar Shukla , Ben Ward

The proliferation of deep neural networks in various domains has seen an increased need for interpretability of these models. Preliminary work done along this line and papers that surveyed such, are focused on high-level representation…

Computation and Language · Computer Science 2022-08-17 Hassan Sajjad , Nadir Durrani , Fahim Dalvi

Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal,…

Software Engineering · Computer Science 2026-03-20 Zhe Yin , Xiaodong Gu , Beijun Shen

Probing large language models (LLMs) has yielded valuable insights into their internal mechanisms by linking neural activations to interpretable semantics. However, the complex mechanisms that link neuron's functional co-activation with the…

Computation and Language · Computer Science 2026-01-30 Yu Zheng , Yuan Yuan , Yue Zhuo , Yong Li , Gabriel Kreiman , Tomaso Poggio , Paolo Santi

Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia…

Computation and Language · Computer Science 2024-06-12 Haowen Pan , Yixin Cao , Xiaozhi Wang , Xun Yang , Meng Wang

While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…

Machine Learning · Computer Science 2025-07-09 Sofiia Chorna , Kateryna Tarelkina , Eloïse Berthier , Gianni Franchi

Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a variety of…

Machine Learning · Computer Science 2024-05-28 Ouail Kitouni , Niklas Nolte , Víctor Samuel Pérez-Díaz , Sokratis Trifinopoulos , Mike Williams

Human brains lie at the core of complex neurobiological systems, where the neurons, circuits, and subsystems interact in enigmatic ways. Understanding the structural and functional mechanisms of the brain has long been an intriguing pursuit…

Neurons and Cognition · Quantitative Biology 2022-07-26 Hejie Cui , Wei Dai , Yanqiao Zhu , Xiaoxiao Li , Lifang He , Carl Yang

Subgraph representation learning has emerged as an important problem, but it is by default approached with specialized graph neural networks on a large global graph. These models demand extensive memory and computational resources but…

Machine Learning · Computer Science 2024-05-24 Dongkwan Kim , Alice Oh

We present a logic based interpretable model for learning on graphs and an algorithm to distill this model from a Graph Neural Network (GNN). Recent results have shown connections between the expressivity of GNNs and the two-variable…

Machine Learning · Computer Science 2024-08-22 Alexander Pluska , Pascal Welke , Thomas Gärtner , Sagar Malhotra

Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs (TAGs), which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are…

Machine Learning · Computer Science 2026-04-23 Peyman Baghershahi , Gregoire Fournier , Pranav Nyati , Sourav Medya

Large language models (LLMs) have demonstrated impressive reasoning abilities in complex tasks. However, they lack up-to-date knowledge and experience hallucinations during reasoning, which can lead to incorrect reasoning processes and…

Computation and Language · Computer Science 2024-02-27 Linhao Luo , Yuan-Fang Li , Gholamreza Haffari , Shirui Pan

The shape and connectivity of a neuron determine its function. Modern imaging methods have proven successful at extracting such information. However, in order to analyze this type of data, neuronal morphology needs to be encoded in a…

Neurons and Cognition · Quantitative Biology 2019-03-07 Tamal Batabyal , Barry Condron , Scott T. Acton

We introduce G2T-LLM, a novel approach for molecule generation that uses graph-to-tree text encoding to transform graph-based molecular structures into a hierarchical text format optimized for large language models (LLMs). This encoding…

Machine Learning · Computer Science 2024-10-04 Zhaoning Yu , Xiangyang Xu , Hongyang Gao

Pretrained language models (PLMs) form the basis of most state-of-the-art NLP technologies. Nevertheless, they are essentially black boxes: Humans do not have a clear understanding of what knowledge is encoded in different parts of the…

Computation and Language · Computer Science 2023-11-15 Tanja Baeumel , Soniya Vijayakumar , Josef van Genabith , Guenter Neumann , Simon Ostermann

Recent models have shown that incorporating syntactic knowledge into the semantic role labelling (SRL) task leads to a significant improvement. In this paper, we propose Syntax-aware Graph-to-Graph Transformer (SynG2G-Tr) model, which…

Computation and Language · Computer Science 2023-06-05 Alireza Mohammadshahi , James Henderson