English
Related papers

Related papers: Localizing Paragraph Memorization in Language Mode…

200 papers

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Andrew Jackson

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Computation and Language · Computer Science 2019-02-01 Thomas Zenkel , Joern Wuebker , John DeNero

Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approaches typically treat all tokens in a response indiscriminately and enforce uncertainty over…

Computation and Language · Computer Science 2026-04-21 Naixin Zhai , Pengyang Shao , Binbin Zheng , Yonghui Yang , Fei Shen , Long Bai , Xun Yang

Neural networks pose a privacy risk due to their propensity to memorise and leak training data. We show that unique features occurring only once in training data are memorised by discriminative multi-layer perceptrons and convolutional…

Machine Learning · Computer Science 2022-05-23 John Hartley , Sotirios A. Tsaftaris

Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability. This study addresses the overlooked impact of subtler, more complex shortcuts that compromise model…

Computation and Language · Computer Science 2024-11-13 Yuqing Zhou , Ruixiang Tang , Ziyu Yao , Ziwei Zhu

While a lot of analysis has been carried to demonstrate linguistic knowledge captured by the representations learned within deep NLP models, very little attention has been paid towards individual neurons.We carry outa neuron-level analysis…

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

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

Machine Learning · Computer Science 2025-06-27 Fei Wang , Baochun Li

In this study, we propose an axiomatic system to define and quantify the precise memorization and in-context reasoning effects used by the large language model (LLM) for language generation. These effects are formulated as non-linear…

Machine Learning · Computer Science 2024-05-21 Siyu Lou , Yuntian Chen , Xiaodan Liang , Liang Lin , Quanshi Zhang

Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does not require any…

Computation and Language · Computer Science 2019-06-06 Hongyin Luo , Lan Jiang , Yonatan Belinkov , James Glass

Many real-world applications require making multiple predictions from the same text. Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward…

Computation and Language · Computer Science 2023-10-17 Kuan-Hao Huang , Liang Tan , Rui Hou , Sinong Wang , Amjad Almahairi , Ruty Rinott

Deep neural networks are over-parameterized and easily overfit the datasets they train on. In the extreme case, it has been shown that these networks can memorize a training set with fully randomized labels. We propose using the curvature…

Machine Learning · Computer Science 2023-10-03 Isha Garg , Deepak Ravikumar , Kaushik Roy

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

Language models are widely used in computational psycholinguistics to test theories that relate the negative log probability (the surprisal) of a region of interest (a substring of characters) under a language model to its cognitive cost…

Computation and Language · Computer Science 2024-12-09 Mario Giulianelli , Luca Malagutti , Juan Luis Gastaldi , Brian DuSell , Tim Vieira , Ryan Cotterell

Pre-trained transformer language models have shown remarkable performance on a variety of NLP tasks. However, recent research has suggested that phrase-level representations in these models reflect heavy influences of lexical content, but…

Computation and Language · Computer Science 2021-06-02 Lang Yu , Allyson Ettinger

Generative large language models (LLMs) excel in natural language processing tasks, yet their inner workings remain underexplored beyond token-level predictions. This study investigates the degree to which these models decide the content of…

Computation and Language · Computer Science 2024-09-11 Nicholas Pochinkov , Angelo Benoit , Lovkush Agarwal , Zainab Ali Majid , Lucile Ter-Minassian

Visually-grounded language models (VLMs) are highly effective in linking visual and textual information, yet they often struggle with basic classification and localization tasks. While classification mechanisms have been studied more…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Timothy Schaumlöffel , Martina G. Vilas , Gemma Roig

Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…

Computation and Language · Computer Science 2025-03-13 Falko Helm , Nico Daheim , Iryna Gurevych

Large Language Models (LLMs) can sometimes degrade into repetitive loops, persistently generating identical word sequences. Because repetition is rare in natural human language, its frequent occurrence across diverse tasks and contexts in…

Computation and Language · Computer Science 2025-11-05 Matéo Mahaut , Francesca Franzon

Sequence models lie at the heart of modern deep learning. However, rapid advancements have produced a diversity of seemingly unrelated architectures, such as Transformers and recurrent alternatives. In this paper, we introduce a unifying…

Machine Learning · Computer Science 2025-05-05 Ke Alexander Wang , Jiaxin Shi , Emily B. Fox

Attention mechanism in sequence-to-sequence models is designed to model the alignments between acoustic features and output tokens in speech recognition. However, attention weights produced by models trained end to end do not always…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-27 Gene-Ping Yang , Hao Tang
‹ Prev 1 8 9 10 Next ›