English
Related papers

Related papers: Mitigating Memorization in LLMs using Activation S…

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

Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Jianghao Yin , Qin Chen , Kedi Chen , Jie Zhou , Xingjiao Wu , Liang He

Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of…

Machine Learning · Computer Science 2026-03-10 Minjae Kang , Jaehyung Kim

Large Language Models (LLMs) memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII), which should not be stored and, consequently, not leaked. In this paper, we introduce Private…

Cryptography and Security · Computer Science 2025-08-22 Elena Sofia Ruzzetti , Giancarlo A. Xompero , Davide Venditti , Fabio Massimo Zanzotto

Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-token training objective that we call the goldfish loss. During…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

While recent research increasingly showcases the remarkable capabilities of Large Language Models (LLMs), it is equally crucial to examine their associated risks. Among these, privacy and security vulnerabilities are particularly…

Computation and Language · Computer Science 2026-01-21 Ali Satvaty , Suzan Verberne , Fatih Turkmen

Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. Existing methods for detecting memorization are primarily…

Cryptography and Security · Computer Science 2026-01-07 Zhenpeng Wu , Jian Lou , Zibin Zheng , Chuan Chen

Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the alignment with a specific target feature direction. However, standard interventions, such as…

Machine Learning · Computer Science 2026-05-05 Tam Nguyen , Tu Anh Nguyen , Sina Alemohammad , Richard G. Baraniuk

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…

Computation and Language · Computer Science 2025-08-21 Badrinath Ramakrishnan , Akshaya Balaji

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Computation and Language · Computer Science 2026-03-13 Mehdi Jafari , Hao Xue , Flora Salim

Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers…

Computation and Language · Computer Science 2025-07-18 Xinyu Tang , Zhihao Lv , Xiaoxue Cheng , Junyi Li , Wayne Xin Zhao , Zujie Wen , Zhiqiang Zhang , Jun Zhou

Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impact of simple pruning techniques on this behavior. Our…

Machine Learning · Computer Science 2025-02-25 Mansi Gupta , Nikhar Waghela , Sarthak Gupta , Shourya Goel , Sanjif Shanmugavelu

Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large ones) bear considerable risk of memorizing private training…

Computation and Language · Computer Science 2022-12-19 C. M. Downey , Wei Dai , Huseyin A. Inan , Kim Laine , Saurabh Naik , Tomasz Religa

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

Machine Learning · Computer Science 2025-12-12 Fu-Chieh Chang , Yu-Ting Lee , Pei-Yuan Wu

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

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

Computation and Language · Computer Science 2026-03-03 Tim Tian Hua , Andrew Qin , Samuel Marks , Neel Nanda

Large Language Models (LLMs) are known to memorize significant portions of their training data. Parts of this memorized content have been shown to be extractable by simply querying the model, which poses a privacy risk. We present a novel…

Computation and Language · Computer Science 2023-05-22 Mustafa Safa Ozdayi , Charith Peris , Jack FitzGerald , Christophe Dupuy , Jimit Majmudar , Haidar Khan , Rahil Parikh , Rahul Gupta

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Machine Learning · Computer Science 2025-03-04 Reza Bayat , Ali Rahimi-Kalahroudi , Mohammad Pezeshki , Sarath Chandar , Pascal Vincent

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

Computation and Language · Computer Science 2026-03-17 Amr Hegazy , Mostafa Elhoushi , Amr Alanwar