English
Related papers

Related papers: Redundancy and Concept Analysis for Code-trained L…

200 papers

Transformer-based deep NLP models are trained using hundreds of millions of parameters, limiting their applicability in computationally constrained environments. In this paper, we study the cause of these limitations by defining a notion of…

Computation and Language · Computer Science 2020-10-07 Fahim Dalvi , Hassan Sajjad , Nadir Durrani , Yonatan Belinkov

Despite substantial efforts, neural network interpretability remains an elusive goal, with previous research failing to provide succinct explanations of most single neurons' impact on the network output. This limitation is due to the…

Machine Learning · Computer Science 2024-02-01 Simon C. Marshall , Jan H. Kirchner

Advances in model editing through neuron pruning hold promise for removing undesirable concepts from large language models. However, it remains unclear whether models have the capacity to reacquire pruned concepts after editing. To…

Artificial Intelligence · Computer Science 2024-01-04 Michelle Lo , Shay B. Cohen , Fazl Barez

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

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

Locating neurons that are responsible for final predictions is important for opening the black-box large language models and understanding the inside mechanisms. Previous studies have tried to find mechanisms that operate at the neuron…

Computation and Language · Computer Science 2025-08-25 Vivek Hruday Kavuri , Gargi Shroff , Rahul Mishra

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained…

Machine Learning · Computer Science 2023-11-15 Vedant Nanda , Till Speicher , John P. Dickerson , Soheil Feizi , Krishna P. Gummadi , Adrian Weller

Current natural language understanding (NLU) models have been continuously scaling up, both in terms of model size and input context, introducing more hidden and input neurons. While this generally improves performance on average, the extra…

Computation and Language · Computer Science 2024-03-12 Yunchang Zhu , Liang Pang , Kangxi Wu , Yanyan Lan , Huawei Shen , Xueqi Cheng

This work proposes the first strategy to make distributed training of neural networks resilient to computing errors, a problem that has remained unsolved despite being first posed in 1956 by von Neumann. He also speculated that the…

Information Theory · Computer Science 2019-03-05 Sanghamitra Dutta , Ziqian Bai , Tze Meng Low , Pulkit Grover

While a lot of work has been done in understanding representations learned within deep NLP models and what knowledge they capture, little attention has been paid towards individual neurons. We present a technique called as Linguistic…

Computation and Language · Computer Science 2024-01-17 Nadir Durrani , Fahim Dalvi , Hassan Sajjad

Overparameterized neural networks often contain many removable neurons, yet what makes a neuron redundant remains poorly understood. Existing pruning criteria commonly rely on local quantities such as weight magnitude, activation strength,…

Machine Learning · Computer Science 2026-05-21 Yongyu Wang

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

Computation and Language · Computer Science 2025-03-26 Joseph Sakau , Evander Kozlowski , Roderick Thistledown , Basil Steinberger

We introduce a framework for reasoning about what meaning is captured by the neurons in a trained neural network. We provide a strategy for discovering meaning by training a second model (referred to as an observer model) to classify the…

Machine Learning · Computer Science 2021-03-16 Eric E. Allen

Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not…

Computation and Language · Computer Science 2023-07-12 Shammur Absar Chowdhury , Nadir Durrani , Ahmed Ali

Large Language Models have demonstrated impressive reasoning capabilities across multiple languages. However, the relationship between capabilities in different languages is less explored. In this work, we decompose the process of reasoning…

Computation and Language · Computer Science 2025-03-04 Peng Hu , Sizhe Liu , Changjiang Gao , Xin Huang , Xue Han , Junlan Feng , Chao Deng , Shujian Huang

While neural networks have been successfully applied to many natural language processing tasks, they come at the cost of interpretability. In this paper, we propose a general methodology to analyze and interpret decisions from a neural…

Computation and Language · Computer Science 2017-01-11 Jiwei Li , Will Monroe , Dan Jurafsky

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Vladimir Zaigrajew , Michał Piechota , Gaspar Sekula , Paweł Gelar , Przemysław Biecek

Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD). We introduce ConceptCoder, a fine-tuning method that…

Software Engineering · Computer Science 2026-03-25 Md Mahbubur Rahman , Hengbo Tong , Wei Le

Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…

Redundant code is a persistent challenge in software development that makes systems harder to maintain, scale, and update. It adds unnecessary complexity, hinders bug fixes, and increases technical debt. Despite their impact, removing…

Software Engineering · Computer Science 2025-05-08 Shamse Tasnim Cynthia
‹ Prev 1 2 3 10 Next ›