English
Related papers

Related papers: Understanding Memorisation in LLMs: Dynamics, Infl…

200 papers

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

To produce accurate predictions, language models (LMs) must balance between generalization and memorization. Yet, little is known about the mechanism by which transformer LMs employ their memorization capacity. When does a model decide to…

Computation and Language · Computer Science 2023-02-14 Adi Haviv , Ido Cohen , Jacob Gidron , Roei Schuster , Yoav Goldberg , Mor Geva

Memorization is a fundamental component of intelligence for both humans and LLMs. However, while LLM performance scales rapidly, our understanding of memorization lags. Due to limited access to the pre-training data of LLMs, most previous…

Computation and Language · Computer Science 2026-03-24 Bowen Chen , Namgi Han , Yusuke Miyao

We investigate how Large Language Models (LLMs) distinguish between memorization and generalization at the neuron level. Through carefully designed tasks, we identify distinct neuron subsets responsible for each behavior. Experiments on…

Computation and Language · Computer Science 2025-07-10 Ko-Wei Huang , Yi-Fu Fu , Ching-Yu Tsai , Yu-Chieh Tu , Tzu-Ling Cheng , Cheng-Yu Lin , Yi-Ting Yang , Heng-Yi Liu , Keng-Te Liao , Da-Cheng Juan , Shou-De Lin

Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a…

Computation and Language · Computer Science 2026-03-04 Xiaoyu Luo , Wenrui Yu , Qiongxiu Li , Johannes Bjerva

Language Models (LMs) are prone to memorizing parts of their data during training and unintentionally emitting them at generation time, raising concerns about privacy leakage and disclosure of intellectual property. While previous research…

Computation and Language · Computer Science 2025-06-12 Stefan Arnold

Large Language Models (LLMs) are known to memorize portions of their training data, sometimes even reproduce content verbatim when prompted appropriately. Despite substantial interest, existing LLM memorization research has offered limited…

Computation and Language · Computer Science 2026-04-21 Yizhan Huang , Zhe Yang , Meifang Chen , Huang Nianchen , Jianping Zhang , Michael R. Lyu

Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood. We empirically study exact memorization in causal and masked language modeling, across model sizes and…

Computation and Language · Computer Science 2022-11-04 Kushal Tirumala , Aram H. Markosyan , Luke Zettlemoyer , Armen Aghajanyan

Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts. Yet linguistic knowledge also encodes relationships between contexts, allowing inferences between word…

Computation and Language · Computer Science 2023-11-09 Michael Wilson , Jackson Petty , Robert Frank

Transformer models are now a cornerstone in natural language processing. Yet, explaining their decisions remains a challenge. It was shown recently that the same model trained on the same data with a different randomness can lead to very…

Computation and Language · Computer Science 2026-03-10 Romain Loncour , Jérémie Bogaert , François-Xavier Standaert

Large language models (LLMs) trained on huge corpora of text datasets demonstrate intriguing capabilities, achieving state-of-the-art performance on tasks they were not explicitly trained for. The precise nature of LLM capabilities is often…

Artificial Intelligence · Computer Science 2024-04-17 Eric J. Bigelow , Ekdeep Singh Lubana , Robert P. Dick , Hidenori Tanaka , Tomer D. Ullman

When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…

Machine Learning · Computer Science 2024-09-05 Eric Zhang , Leshem Chosen , Jacob Andreas

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

Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLMs' context…

Computation and Language · Computer Science 2025-07-11 Yuepei Li , Kang Zhou , Qiao Qiao , Bach Nguyen , Qing Wang , Qi Li

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Sunny Duan , Mikail Khona , Abhiram Iyer , Rylan Schaeffer , Ila R Fiete

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

Transformer-based Large Language Models (LLMs) have revolutionized Natural Language Processing by demonstrating exceptional performance across diverse tasks. This study investigates the impact of the parameter initialization scale on the…

Computation and Language · Computer Science 2025-05-22 Junjie Yao , Zhongwang Zhang , Zhi-Qin John Xu

We introduce the framework of "social learning" in the context of large language models (LLMs), whereby models share knowledge with each other in a privacy-aware manner using natural language. We present and evaluate two approaches for…

Machine Learning · Computer Science 2024-02-09 Amirkeivan Mohtashami , Florian Hartmann , Sian Gooding , Lukas Zilka , Matt Sharifi , Blaise Aguera y Arcas

Memory, a fundamental component of human cognition, exhibits adaptive yet fallible characteristics as illustrated by Schacter's memory "sins".These cognitive phenomena have been studied extensively in psychology and neuroscience, but the…

Neurons and Cognition · Quantitative Biology 2025-10-23 Zhaoyang Cao , Lael Schooler , Reza Zafarani

Large language models are known to memorize parts of their training data, posing risk of copyright violations. To systematically examine this risk, we pretrain language models (1B/3B/8B) from scratch on 83B tokens, mixing web-scale data…

Computation and Language · Computer Science 2025-05-29 Yixuan Xu , Antoni-Joan Solergibert i Llaquet , Antoine Bosselut , Imanol Schlag