English
Related papers

Related papers: Mitigating Memorization in LLMs using Activation S…

200 papers

Training large language models (LLMs) is highly memory-intensive, as training must store not only weights and optimizer states but also intermediate activations for backpropagation. While existing memory-efficient methods largely focus on…

Machine Learning · Computer Science 2026-05-05 Wen-Da Wei , Han-Bin Fang , Yang-Di Liu , Jiang-Xin Shi , James Kwok , Yu-Feng Li

Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information. To mitigate privacy risks and safeguard the right to be forgotten, machine unlearning has emerged as a promising approach for…

Cryptography and Security · Computer Science 2025-06-11 Jiacheng Du , Zhibo Wang , Jie Zhang , Xiaoyi Pang , Jiahui Hu , Kui Ren

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

Large Language Models (LLMs) exhibit remarkable capabilities across various tasks, yet guiding them to follow desired behaviours during inference remains a significant challenge. Activation steering offers a promising method to control the…

Computation and Language · Computer Science 2025-09-29 Weixuan Wang , Minghao Wu , Barry Haddow , Alexandra Birch

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

We address the challenge of societal bias in Large Language Models (LLMs), focusing on the Llama 2 7B Chat model. As LLMs are increasingly integrated into decision-making processes with substantial societal impact, it becomes imperative to…

Computation and Language · Computer Science 2024-02-02 Dawn Lu , Nina Rimsky

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially…

Machine Learning · Computer Science 2026-02-17 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Y. Rogov , Ivan Oseledets , Elena Tutubalina

The objective of digital forgetting is, given a model with undesirable knowledge or behavior, obtain a new model where the detected issues are no longer present. The motivations for forgetting include privacy protection, copyright…

Cryptography and Security · Computer Science 2025-01-14 Alberto Blanco-Justicia , Najeeb Jebreel , Benet Manzanares , David Sánchez , Josep Domingo-Ferrer , Guillem Collell , Kuan Eeik Tan

Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for safely deploying language models. In particular, it is vital to minimize a model's memorization…

Computation and Language · Computer Science 2023-06-02 Stella Biderman , USVSN Sai Prashanth , Lintang Sutawika , Hailey Schoelkopf , Quentin Anthony , Shivanshu Purohit , Edward Raff

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Computation and Language · Computer Science 2025-06-05 Jiuding Sun , Sidharth Baskaran , Zhengxuan Wu , Michael Sklar , Christopher Potts , Atticus Geiger

Large Language models (LLMs) are trained on large amounts of data, which can include sensitive information that may compromise personal privacy. LLMs showed to memorize parts of the training data and emit those data verbatim when an…

Computation and Language · Computer Science 2023-05-03 Aly M. Kassem

Large Language Models (LLMs) are increasingly applied in recommendation scenarios due to their strong natural language understanding and generation capabilities. However, they are trained on vast corpora whose contents are not publicly…

Information Retrieval · Computer Science 2026-01-06 Antonio Colacicco , Vito Guida , Dario Di Palma , Fedelucio Narducci , Tommaso Di Noia

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Machine Learning · Computer Science 2026-02-03 Parmida Davarmanesh , Ashia Wilson , Adityanarayanan Radhakrishnan

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Large Language Model (LLM) agents have become increasingly prevalent across various real-world applications. They enhance decision-making by storing private user-agent interactions in the memory module for demonstrations, introducing new…

Cryptography and Security · Computer Science 2025-06-04 Bo Wang , Weiyi He , Shenglai Zeng , Zhen Xiang , Yue Xing , Jiliang Tang , Pengfei He

Large language models (LLMs) often encode cognitive behaviors unpredictably across prompts, layers, and contexts, making them difficult to diagnose and control. We present CBMAS, a diagnostic framework for continuous activation steering,…

Artificial Intelligence · Computer Science 2026-01-13 Ahmed H. Ismail , Anthony Kuang , Ayo Akinkugbe , Kevin Zhu , Sean O'Brien

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Cryptography and Security · Computer Science 2026-03-18 Ali Raza , Gurang Gupta , Nikolay Matyunin , Jibesh Patra

As the development and application of Large Language Models (LLMs) continue to advance rapidly, enhancing their trustworthiness and aligning them with human preferences has become a critical area of research. Traditional methods rely…

Computation and Language · Computer Science 2024-11-06 Yuxin Xiao , Chaoqun Wan , Yonggang Zhang , Wenxiao Wang , Binbin Lin , Xiaofei He , Xu Shen , Jieping Ye

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Machine Learning · Computer Science 2026-03-09 Kartik Sharma , Rakshit S. Trivedi

Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating…

Artificial Intelligence · Computer Science 2026-05-11 Aayush Mishra , Daniel Khashabi , Anqi Liu
‹ Prev 1 3 4 5 6 7 10 Next ›