English
Related papers

Related papers: Negative Pre-activations Differentiate Syntax

200 papers

Large language models (LLMs) have revolutionized the field of natural language processing (NLP), and recent studies have aimed to understand their underlying mechanisms. However, most of this research is conducted within a monolingual…

Computation and Language · Computer Science 2025-09-29 Weixuan Wang , Barry Haddow , Minghao Wu , Wei Peng , Alexandra Birch

Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers.…

Machine Learning · Computer Science 2024-02-20 Chinmay Rane , Kanishka Tyagi , Michael Manry

Large Language Models frequently generate fluent but factually incorrect text. We propose Adaptive Activation Cancellation (AAC), a real-time inference-time framework that treats hallucination-associated neural activations as structured…

Computation and Language · Computer Science 2026-03-12 Eric Yocam , Varghese Vaidyan , Gurcan Comert , Paris Kalathas , Yong Wang , Judith L. Mwakalonge

The input space of a neural network with ReLU-like activations is partitioned into multiple linear regions, each corresponding to a specific activation pattern of the included ReLU-like activations. We demonstrate that this partition…

Machine Learning · Computer Science 2021-01-15 Fengxiang He , Shiye Lei , Jianmin Ji , Dacheng Tao

Negation remains a persistent challenge for modern language models, often causing reversed meanings or factual errors. In this work, we conduct a causal analysis of how GPT-2 Small internally processes such linguistic transformations. We…

Computation and Language · Computer Science 2026-03-16 Abdullah Al Mofael , Lisa M. Kuhn , Ghassan Alkadi , Kuo-Pao Yang

Feed-forward ReLU neural networks partition their input domain into finitely many "affine regions" of constant neuron activation pattern and affine behaviour. We analyze their mathematical structure and provide algorithmic primitives for an…

Optimization and Control · Mathematics 2021-03-09 Peter Hinz , Sara van de Geer

To decipher the algorithm underlying the human brain's language representation, previous work probed brain responses to language input with pre-trained artificial neural network (ANN) models fine-tuned on NLU tasks. However, full…

Artificial Intelligence · Computer Science 2023-10-04 Jingyuan Sun , Marie-Francine Moens

Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit. Given the finite size of realistic DNN, we utilize the large deviation theory and path integral analysis to study the deviation…

Disordered Systems and Neural Networks · Physics 2020-02-21 Bo Li , David Saad

Activation functions are fundamental to deep neural networks, governing gradient flow, optimization stability, and representational capacity. Within historic deep architectures, while ReLU has been the dominant choice for the activation…

Machine Learning · Computer Science 2026-03-10 Mingi Kang , Zai Yang , Jeova Farias Sales Rocha Neto

Recent research has found that the activation function (AF) selected for adding non-linearity into the output can have a big impact on how effectively deep learning networks perform. Developing activation functions that can adapt…

Neural and Evolutionary Computing · Computer Science 2023-06-06 Ashish Rajanand , Pradeep Singh

Deep learning has been widely used in many fields, but the model training process usually consumes massive computational resources and time. Therefore, designing an efficient neural network training method with a provable convergence…

Machine Learning · Computer Science 2023-07-14 Lianke Qin , Zhao Song , Yuanyuan Yang

Deep neural networks, which employ batch normalization and ReLU-like activation functions, suffer from instability in the early stages of training due to the high gradient induced by temporal gradient explosion. In this study, we analyze…

Machine Learning · Computer Science 2023-05-23 Inyoung Paik , Jaesik Choi

Concerns about interpretability, computational resources, and principled inductive priors have motivated efforts to engineer sparse neural models for NLP tasks. If sparsity is important for NLP, might well-trained neural models naturally…

Computation and Language · Computer Science 2019-08-07 Naomi Saphra , Adam Lopez

Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low interpretability. We propose a method for alignment that…

Machine Learning · Computer Science 2026-01-28 Claire O'Brien , Jessica Seto , Dristi Roy , Aditya Dwivedi , Sunishchal Dev , Kevin Zhu , Sean O'Brien , Ashwinee Panda , Ryan Lagasse

We derive approximation bounds for learning single neuron models using thresholded gradient descent when both the labels and the covariates are possibly corrupted adversarially. We assume the data follows the model $y =…

Machine Learning · Statistics 2024-09-06 Arvind Rathnashyam , Alex Gittens

The application of the deep learning model in classification plays an important role in the accurate detection of the target objects. However, the accuracy is affected by the activation function in the hidden and output layer. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-05-22 Md. Mehedi Hasan , Md. Ali Hossain , Azmain Yakin Srizon , Abu Sayeed

Prior work on probing neural networks primarily relies on input-space analysis or parameter perturbation, both of which face fundamental limitations in accessing structural information encoded in intermediate representations. We introduce…

Machine Learning · Computer Science 2026-02-04 Tao Ren , Xiaoyu Luo , Qiongxiu Li

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Binhui Xie , Longhui Yuan , Shuang Li , Chi Harold Liu , Xinjing Cheng

Over the past few years, there has been a significant amount of research focused on studying the ReLU activation function, with the aim of achieving neural network convergence through over-parametrization. However, recent developments in…

Machine Learning · Computer Science 2023-03-30 Yeqi Gao , Sridhar Mahadevan , Zhao Song

In this work, we systematically investigate the efficacy of dynamic activation mechanisms within the LLaMA family of language models. Despite the potential of dynamic activation methods to reduce computation and increase speed in models…

Machine Learning · Computer Science 2024-05-16 Chi Ma , Mincong Huang , Chao Wang , Yujie Wang , Lei Yu