English
Related papers

Related papers: Understanding Gated Neurons in Transformers from T…

200 papers

Our understanding of neural computation is founded on the assumption that neurons fire in response to a linear summation of inputs. Yet experiments demonstrate that some neurons are capable of complex functions that require interactions…

Biological Physics · Physics 2026-03-23 Christopher W. Lynn

Experimental results in recent years have shown that adult neurogenesis is a significant phenomenon in the mammalian brain. Little is known, however, about the functional role played by the generation and destruction of neurons in the…

Neurons and Cognition · Quantitative Biology 2009-11-10 Guillermo A. Cecchi , Marcelo O. Magnasco

Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual representations within these models, it remains unclear whether they functionally rely on…

Computation and Language · Computer Science 2026-04-21 Ningyu Xu , Qi Zhang , Xipeng Qiu , Xuanjing Huang

Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity, known as working memory, is fundamental to human reasoning and intelligence. Despite…

Machine Learning · Computer Science 2026-04-14 Hua-Dong Xiong , Li Ji-An , Jiaqi Huang , Robert C. Wilson , Kwonjoon Lee , Xue-Xin Wei

Language models (LMs) are said to be exhibiting reasoning, but what does this entail? We assess definitions of reasoning and how key papers in the field of natural language processing (NLP) use the notion and argue that the definitions…

Computation and Language · Computer Science 2025-11-18 Bertram Højer

Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not…

Machine Learning · Computer Science 2023-03-10 Han Xuanyuan , Pietro Barbiero , Dobrik Georgiev , Lucie Charlotte Magister , Pietro Lió

Encoding and decoding models are widely used in systems, cognitive, and computational neuroscience to make sense of brain-activity data. However, the interpretation of their results requires care. Decoding models can help reveal whether…

Neurons and Cognition · Quantitative Biology 2019-04-29 Nikolaus Kriegeskorte , Pamela K. Douglas

Conceptual and mathematical models of neurons have lagged behind empirical understanding for decades. Here we extend previous work in modeling biological systems with fully scale-independent quantum information-theoretic tools to develop a…

Neurons and Cognition · Quantitative Biology 2022-07-21 Chris Fields , James F. Glazebrook , Michael Levin

We introduce a new dataset of logical entailments for the purpose of measuring models' ability to capture and exploit the structure of logical expressions against an entailment prediction task. We use this task to compare a series of…

Neural and Evolutionary Computing · Computer Science 2018-02-26 Richard Evans , David Saxton , David Amos , Pushmeet Kohli , Edward Grefenstette

Weight space learning is an emerging paradigm in the deep learning community. The primary goal of weight space learning is to extract informative features from a set of parameters using specially designed neural networks, often referred to…

Machine Learning · Computer Science 2025-03-13 Taesun Yeom , Jaeho Lee

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Computation and Language · Computer Science 2024-11-11 Mansi Sakarvadia

Large language models (LLMs) store extensive factual knowledge, but the underlying mechanisms remain unclear. Previous research suggests that factual knowledge is stored within multi-layer perceptron weights, and some storage units exhibit…

Computation and Language · Computer Science 2024-06-18 Yuheng Chen , Pengfei Cao , Yubo Chen , Yining Wang , Shengping Liu , Kang Liu , Jun Zhao

Natural language is an appealing medium for explaining how large language models process and store information, but evaluating the faithfulness of such explanations is challenging. To help address this, we develop two modes of evaluation…

Computation and Language · Computer Science 2023-09-20 Jing Huang , Atticus Geiger , Karel D'Oosterlinck , Zhengxuan Wu , Christopher Potts

How related are the representations learned by neural language models, translation models, and language tagging tasks? We answer this question by adapting an encoder-decoder transfer learning method from computer vision to investigate the…

Computation and Language · Computer Science 2025-12-11 Richard Antonello , Javier Turek , Vy Vo , Alexander Huth

Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in…

Computation and Language · Computer Science 2023-12-21 Yuheng Chen , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb

Explicit structural information has been proven to be encoded by Graph Neural Networks (GNNs), serving as auxiliary knowledge to enhance model capabilities and improve performance in downstream NLP tasks. However, recent studies indicate…

Computation and Language · Computer Science 2025-06-30 Li Zhou , Hao Jiang , Junjie Li , Zefeng Zhao , Feng Jiang , Wenyu Chen , Haizhou Li

The greatest ambition of mechanistic interpretability is to completely rewrite deep neural networks in a format that is more amenable to human understanding, while preserving their behavior and performance. In this paper, we attempt to…

Machine Learning · Computer Science 2025-02-03 Gonçalo Paulo , Nora Belrose

Understanding the function of individual neurons within language models is essential for mechanistic interpretability research. We propose $\textbf{Neuron to Graph (N2G)}$, a tool which takes a neuron and its dataset examples, and…

Machine Learning · Computer Science 2023-04-26 Alex Foote , Neel Nanda , Esben Kran , Ionnis Konstas , Fazl Barez

Graph neural networks (GNNs), as the de-facto model class for representation learning on graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional message passing layers to allow features to flow across nodes.…

Machine Learning · Computer Science 2023-08-07 Chenxiao Yang , Qitian Wu , Jiahua Wang , Junchi Yan