English
Related papers

Related papers: Positional Fragility in LLMs: How Offset Effects R…

200 papers

Pretrained large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation. However, LLMs pose significant security risks due to their tendency to memorize…

Computation and Language · Computer Science 2024-09-24 Zhepeng Wang , Runxue Bao , Yawen Wu , Jackson Taylor , Cao Xiao , Feng Zheng , Weiwen Jiang , Shangqian Gao , Yanfu Zhang

Understanding whether and to what extent large language models (LLMs) have memorised training data has important implications for the reliability of their output and the privacy of their training data. In order to cleanly measure and…

Computation and Language · Computer Science 2024-07-30 Till Speicher , Mohammad Aflah Khan , Qinyuan Wu , Vedant Nanda , Soumi Das , Bishwamittra Ghosh , Krishna P. Gummadi , Evimaria Terzi

Large language models (LLMs) are increasingly deployed in decision-support systems for high-stakes domains such as hiring and university admissions, where choices often involve selecting among competing alternatives. While prior work has…

Artificial Intelligence · Computer Science 2026-04-15 Haonan Yin , Shai Vardi , Vidyanand Choudhary

Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing…

Machine Learning · Computer Science 2023-03-07 Nicholas Carlini , Daphne Ippolito , Matthew Jagielski , Katherine Lee , Florian Tramer , Chiyuan Zhang

Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. Existing analyses focus on average-case scenarios, often neglecting the highly skewed…

Artificial Intelligence · Computer Science 2025-02-04 Hao Li , Di Huang , Ziyu Wang , Amir M. Rahmani

Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While prefix-augmented inference is effective, it incurs two structural limitations: i) the prefix's…

Computation and Language · Computer Science 2026-05-19 Yasuyuki Okoshi , Hao Mark Chen , Guanxi Lu , Hongxiang Fan , Masato Motomura , Daichi Fujiki

Large Language Models (LLMs) often struggle to use information across long inputs effectively. Prior work has identified positional biases, such as the Lost in the Middle (LiM) effect, where models perform better when information appears at…

Computation and Language · Computer Science 2025-08-12 Blerta Veseli , Julian Chibane , Mariya Toneva , Alexander Koller

Memorization in large language models poses critical risks for privacy and fairness as these systems scale to billions of parameters. While previous studies established correlations between memorization and factors like token frequency and…

Machine Learning · Computer Science 2025-09-01 Jie Zhang , Qinghua Zhao , Chi-ho Lin , Zhongfeng Kang , Lei Li

Large language models, trained on massive corpora, are prone to verbatim memorization of training data, creating significant privacy and copyright risks. While previous works have proposed various definitions for memorization, many exhibit…

Computation and Language · Computer Science 2025-11-27 Trung Cuong Dang , David Mohaisen

Underlying mechanisms of memorization in LLMs -- the verbatim reproduction of training data -- remain poorly understood. What exact part of the network decides to retrieve a token that we would consider as start of memorization sequence?…

Computation and Language · Computer Science 2026-02-04 Ilya Lasy , Peter Knees , Stefan Woltran

Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk is distinguishing genuine memorization of training data from…

Machine Learning · Computer Science 2026-02-24 Trishita Tiwari , Ari Trachtenberg , G. Edward Suh

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

Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…

Computation and Language · Computer Science 2026-03-26 Avni Mittal

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) 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

Large Language Models (LLMs) frequently memorize long sequences verbatim, often with serious legal and privacy implications. Much prior work has studied such verbatim memorization using observational data. To complement such work, we…

Computation and Language · Computer Science 2024-07-26 Jing Huang , Diyi Yang , Christopher Potts

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

Cryptography and Security · Computer Science 2025-07-16 Jérémie Dentan , Davide Buscaldi , Aymen Shabou , Sonia Vanier

As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is often employed to improve model performance, it can…

Computation and Language · Computer Science 2026-02-24 Punya Syon Pandey , Samuel Simko , Kellin Pelrine , Zhijing Jin

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

The performance of Large Language Models (LLMs) often degrades when crucial information is in the middle of a long context, a "lost-in-the-middle" phenomenon that mirrors the primacy and recency effects in human memory. We propose that this…

Machine Learning · Computer Science 2025-10-14 Nikolaus Salvatore , Hao Wang , Qiong Zhang
‹ Prev 1 2 3 10 Next ›