paper-with-me

Papers

Mitigating Memorization in LLMs using Activation Steering

2025-03-08 · Manan Suri, Nishit Anand, Amisha Bhaskar

The memorization of training data by Large Language Models (LLMs) poses significant risks, including privacy leaks and the regurgitation of copyrighted content. Activation steering, a technique that directly intervenes in model activations, has emerged as a promising approach for manipulating LLMs. In this work, we explore the effectiveness of activation steering in reducing memorization while preserving generalization capabilities. We conduct empirical evaluations using a controlled memorization benchmark of literary material and demonstrate that our method successfully suppresses memorized content with minimal degradation in model performance in Gemma. Additionally, we analyze the trade-offs between suppression effectiveness and linguistic fluency, highlighting the advantages and limitations of activation-based interventions. Our findings contribute to ongoing efforts in developing safer and more privacy-preserving LLMs by providing a practical and efficient mechanism to mitigate unintended memorization.

📄 PDF Abstract BibTeX arXiv:2503.06040

Code (0)

등록된 구현이 없습니다.

Tasks

MemorizationPrivacy Preserving

Similar Papers 제목 키워드 기반

GSS: Gated Subspace Steering for Selective Memorization Mitigation in LLMs

2026-02-09 · Xuanqi Zhang, Haoyang Shang, Xiaoxiao Li arxiv

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading perf…

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering

2025-05-18 · Marco Valentino, Geonhee Kim, Dhairya Dalal, Zhixue Zhao 외

Large language models (LLMs) frequently demonstrate reasoning limitations, often conflating content plausibility (i.e., material inference) with logical validity (i.e., formal inference). This can result in biased infere…

Language ModelingLanguage Modelling

Extracting Unlearned Information from LLMs with Activation Steering

2024-11-04 · Atakan Seyitoğlu, Aleksei Kuvshinov, Leo Schwinn, Stephan Günnemann

An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or copyrighted information. In recent years,…

General KnowledgeInformation RetrievalMemorizationRetrieval

Generalization or Memorization: Dynamic Decoding for Mode Steering

2025-10-25 · Xuanming Zhang arxiv

Large Language Models (LLMs) exhibit a troubling duality, capable of both remarkable generalization and brittle, verbatim memorization of their training data. This unpredictability undermines their reliability in high-st…

SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering

2024-08-21 · Zouying Cao, Yifei Yang, Hai Zhao

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerate…

Safety Alignment