English
Related papers

Related papers: Modifying Memories in Transformer Models

200 papers

Recent research demonstrated that training large language models involves memorization of a significant fraction of training data. Such memorization can lead to privacy violations when training on sensitive user data and thus motivates the…

Machine Learning · Computer Science 2025-10-29 Vitaly Feldman , Guy Kornowski , Xin Lyu

Large pre-trained language models have demonstrated their proficiency in storing factual knowledge within their parameters and achieving remarkable results when fine-tuned for downstream natural language processing tasks. Nonetheless, their…

Computation and Language · Computer Science 2023-09-29 Konstantinos Andriopoulos , Johan Pouwelse

Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data, which can compromise evaluation metrics, raise privacy concerns, and limit…

Machine Learning · Computer Science 2024-12-03 Eduardo Slonski

Understanding how large language models (LLMs) acquire and store factual knowledge is crucial for enhancing their interpretability and reliability. In this work, we analyze the evolution of factual knowledge representation in the OLMo-7B…

Computation and Language · Computer Science 2025-06-05 Ahmad Dawar Hakimi , Ali Modarressi , Philipp Wicke , Hinrich Schütze

Pre-trained Language Models (PLMs) encode various facts about the world at their pre-training phase as they are trained to predict the next or missing word in a sentence. There has a been an interest in quantifying and improving the amount…

Computation and Language · Computer Science 2024-10-18 Paul Youssef , Jörg Schlötterer , Christin Seifert

Transformers are responsible for the vast majority of recent advances in natural language processing. The majority of practical natural language processing applications of these models are typically enabled through transfer learning. This…

Computation and Language · Computer Science 2024-02-02 Vladislav Mosin , Igor Samenko , Alexey Tikhonov , Borislav Kozlovskii , Ivan P. Yamshchikov

The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we…

Computation and Language · Computer Science 2025-03-04 Xinyi Wang , Antonis Antoniades , Yanai Elazar , Alfonso Amayuelas , Alon Albalak , Kexun Zhang , William Yang Wang

Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting…

Artificial Intelligence · Computer Science 2025-11-26 Zhen Zeng , Leijiang Gu , Zhangling Duan , Feng Li , Zenglin Shi , Cees G. M. Snoek , Meng Wang

Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors. This is to encourage them to learn in ways that are compatible with our…

Machine Learning · Computer Science 2022-10-25 Kristy Choi , Chris Cundy , Sanjari Srivastava , Stefano Ermon

Rote learning is a memorization technique based on repetition. Many researchers argue that rote learning hinders generalization because it encourages verbatim memorization rather than deeper understanding. This concern extends even to…

Computation and Language · Computer Science 2026-03-03 Qinyuan Wu , Soumi Das , Mahsa Amani , Bishwamittra Ghosh , Mohammad Aflah Khan , Krishna P. Gummadi , Muhammad Bilal Zafar

Transformer-based models are now predominant in NLP. They outperform approaches based on static models in many respects. This success has in turn prompted research that reveals a number of biases in the language models generated by…

Computation and Language · Computer Science 2022-04-13 Alexander Henlein , Alexander Mehler

Large Language Models demonstrate remarkable mathematical capabilities but at the same time struggle with abstract reasoning and planning. In this study, we explore whether Transformers can learn to abstract and generalize the rules…

Neural and Evolutionary Computing · Computer Science 2024-12-03 Mikhail Burtsev

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

Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vast corpus of texts from various sources; despite the best…

Computation and Language · Computer Science 2024-11-26 Abhinav Joshi , Shaswati Saha , Divyaksh Shukla , Sriram Vema , Harsh Jhamtani , Manas Gaur , Ashutosh Modi

Transformers are neural networks that revolutionized natural language processing and machine learning. They process sequences of inputs, like words, using a mechanism called self-attention, which is trained via masked language modeling…

Disordered Systems and Neural Networks · Physics 2024-04-17 Riccardo Rende , Federica Gerace , Alessandro Laio , Sebastian Goldt

Language models excel in various tasks by making complex decisions, yet understanding the rationale behind these decisions remains a challenge. This paper investigates \emph{data-centric interpretability} in language models, focusing on the…

Computation and Language · Computer Science 2025-06-10 Yuqian Li , Yupei Du , Yufang Liu , Feifei Feng , Mou Xiao Feng , Yuanbin Wu

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…

Computation and Language · Computer Science 2026-02-25 Yanbo Dai , Zhenlan Ji , Zongjie Li , Shuai Wang

The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…

Machine Learning · Computer Science 2023-05-09 Riccardo Ughi , Eugenio Lomurno , Matteo Matteucci

Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating responses to complex queries through large-scale pre-training. However, the efficacy of these models in memorizing and reasoning among…

Computation and Language · Computer Science 2024-02-23 Qiyuan He , Yizhong Wang , Wenya Wang

With the development of large language models (LLMs) like the GPT series, their widespread use across various application scenarios presents a myriad of challenges. This review initially explores the issue of domain specificity, where LLMs…

Computation and Language · Computer Science 2023-10-23 Xiaoliang Chen , Liangbin Li , Le Chang , Yunhe Huang , Yuxuan Zhao , Yuxiao Zhang , Dinuo Li