English
Related papers

Related papers: Measuring Memorization Effect in Word-Level Neural…

200 papers

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks,…

Machine Learning · Computer Science 2025-12-15 Alexander Xiong , Xuandong Zhao , Aneesh Pappu , Dawn Song

Pre-trained contextual representations have led to dramatic performance improvements on a range of downstream tasks. Such performance improvements have motivated researchers to quantify and understand the linguistic information encoded in…

Computation and Language · Computer Science 2022-03-28 Alexander Immer , Lucas Torroba Hennigen , Vincent Fortuin , Ryan Cotterell

We propose a new method for estimating how much a model knows about a datapoint and use it to measure the capacity of modern language models. Prior studies of language model memorization have struggled to disentangle memorization from…

Edge probing tests are classification tasks that test for grammatical knowledge encoded in token representations coming from contextual encoders such as large language models (LLMs). Many LLM encoders have shown high performance in EP…

Computation and Language · Computer Science 2023-10-24 Sagnik Ray Choudhury , Jushaan Kalra

Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We…

Machine Learning · Computer Science 2022-12-09 Mahsa Forouzesh , Hanie Sedghi , Patrick Thiran

We present an empirical evaluation of various outputs generated by nine of the most widely-available large language models (LLMs). Our analysis is done with off-the-shelf, readily-available tools. We find a correlation between percentage of…

Computation and Language · Computer Science 2026-01-12 Adrian de Wynter , Xun Wang , Alex Sokolov , Qilong Gu , Si-Qing Chen

Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is spread across multiple layers and model components,…

Computation and Language · Computer Science 2024-04-01 Niklas Stoehr , Mitchell Gordon , Chiyuan Zhang , Owen Lewis

Recent advances in deep generative models have led to impressive results in a variety of application domains. Motivated by the possibility that deep learning models might memorize part of the input data, there have been increased efforts to…

Machine Learning · Computer Science 2021-12-30 Gerrit J. J. van den Burg , Christopher K. I. Williams

Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…

Computation and Language · Computer Science 2023-11-07 Zhenhong Zhou , Jiuyang Xiang , Chaomeng Chen , Sen Su

We empirically investigate the impact of learning randomly generated labels in parallel to class labels in supervised learning on memorization, model complexity, and generalization in deep neural networks. To this end, we introduce a…

Machine Learning · Computer Science 2024-12-02 Marlon Becker , Benjamin Risse

Large Language Models (LLMs), trained on massive corpora with billions of parameters, show unprecedented performance in various fields. Though surprised by their excellent performances, researchers also noticed some special behaviors of…

Computation and Language · Computer Science 2024-06-05 Bowen Chen , Namgi Han , Yusuke Miyao

Machine learning models are known to memorize samples from their training data, raising concerns around privacy and generalization. Counterfactual self-influence is a popular metric to study memorization, quantifying how the model's…

Machine Learning · Computer Science 2025-06-26 Matthieu Meeus , Igor Shilov , Georgios Kaissis , Yves-Alexandre de Montjoye

Sample selection approaches are popular in robust learning from noisy labels. However, how to properly control the selection process so that deep networks can benefit from the memorization effect is a hard problem. In this paper, motivated…

Machine Learning · Computer Science 2020-09-21 Quanming Yao , Hansi Yang , Bo Han , Gang Niu , James Kwok

The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of…

Computation and Language · Computer Science 2025-08-08 Karolina Stańczak , Lucas Torroba Hennigen , Adina Williams , Ryan Cotterell , Isabelle Augenstein

Non-native speakers show difficulties with spoken word processing. Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. We test an alternative hypothesis: that some of these…

Computation and Language · Computer Science 2021-03-12 Yevgen Matusevych , Herman Kamper , Thomas Schatz , Naomi H. Feldman , Sharon Goldwater

Memorization presents a challenge for several constrained Natural Language Generation (NLG) tasks such as Neural Machine Translation (NMT), wherein the proclivity of neural models to memorize noisy and atypical samples reacts adversely with…

Computation and Language · Computer Science 2022-10-25 Vikas Raunak , Arul Menezes

Do word embeddings converge to learn similar things over different initializations? How repeatable are experiments with word embeddings? Are all word embedding techniques equally reliable? In this paper we propose evaluating methods for…

Computation and Language · Computer Science 2016-05-13 Yingtao Tian , Vivek Kulkarni , Bryan Perozzi , Steven Skiena

This work analyses the text memorization behavior of large language models (LLMs) when subjected to nucleus sampling. Stochastic decoding methods like nucleus sampling are typically applied to overcome issues such as monotonous and…

Computation and Language · Computer Science 2024-08-30 Luka Borec , Philipp Sadler , David Schlangen

Word Embeddings are used widely in multiple Natural Language Processing (NLP) applications. They are coordinates associated with each word in a dictionary, inferred from statistical properties of these words in a large corpus. In this paper…

Computation and Language · Computer Science 2020-06-18 Adam Sutton , Nello Cristianini

State-of-the-art pre-trained language models have been shown to memorise facts and perform well with limited amounts of training data. To gain a better understanding of how these models learn, we study their generalisation and memorisation…

Computation and Language · Computer Science 2022-03-16 Michael Tänzer , Sebastian Ruder , Marek Rei