Image de couverture de livre

Mitigating Memorization in LLMs using Activation Steering

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Suri, Manan, Anand, Nishit, Bhaskar, Amisha
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
par: Hans, Abhimanyu, et autres
Publié: (2024)

Learning Illumination Control in Diffusion Models
par: Anand, Nishit, et autres
Publié: (2026)

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
par: Li, Yichen, et autres
Publié: (2025)

Generalization or Memorization: Dynamic Decoding for Mode Steering
par: Zhang, Xuanming
Publié: (2025)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
par: Xiong, Alexander, et autres
Publié: (2025)

Continual Memorization of Factoids in Language Models
par: Chen, Howard, et autres
Publié: (2024)

Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs
par: Bossy, Thierry, et autres
Publié: (2025)

Steering Towards Fairness: Mitigating Political Bias in LLMs
par: Nadeem, Afrozah, et autres
Publié: (2025)

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
par: Wang, Weixuan, et autres
Publié: (2024)

Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
par: Lucchetti, Francesca, et autres
Publié: (2024)

Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs
par: Joshi, Kunj, et autres
Publié: (2025)

Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs
par: Hegazy, Amr, et autres
Publié: (2025)

Steering MoE LLMs via Expert (De)Activation
par: Fayyaz, Mohsen, et autres
Publié: (2025)

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
par: Yan, Lecheng, et autres
Publié: (2026)

Mitigating Memorization In Language Models
par: Sakarvadia, Mansi, et autres
Publié: (2024)

The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization
par: Borec, Luka, et autres
Publié: (2024)

Extracting Unlearned Information from LLMs with Activation Steering
par: Seyitoğlu, Atakan, et autres
Publié: (2024)

SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering
par: Maskey, Utsav, et autres
Publié: (2025)

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
par: Kassem, Aly M., et autres
Publié: (2024)

Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering
par: Gupta, Manan, et autres
Publié: (2026)

Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
par: Bhandari, Pranav, et autres
Publié: (2025)

Fine-Grained Activation Steering: Steering Less, Achieving More
par: Feng, Zijian, et autres
Publié: (2026)

Memorization or Reasoning? Exploring the Idiom Understanding of LLMs
par: Kim, Jisu, et autres
Publié: (2025)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
par: Anand, Nikhil, et autres
Publié: (2026)

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
par: Siddique, Zara, et autres
Publié: (2025)

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
par: Valentino, Marco, et autres
Publié: (2025)

Skeleton-based Coherence Modeling in Narratives
par: Asnani, Nishit, et autres
Publié: (2026)

Steer2Edit: From Activation Steering to Component-Level Editing
par: Sun, Chung-En, et autres
Publié: (2026)

Memorization and Knowledge Injection in Gated LLMs
par: Pan, Xu, et autres
Publié: (2025)

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks
par: Ruan, Zhiwen, et autres
Publié: (2025)

Understanding Verbatim Memorization in LLMs Through Circuit Discovery
par: Lasy, Ilya, et autres
Publié: (2025)

Steering Awareness: Detecting Activation Steering from Within
par: Rivera, Joshua Fonseca, et autres
Publié: (2025)

ChartLens: Fine-grained Visual Attribution in Charts
par: Suri, Manan, et autres
Publié: (2025)

VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation
par: Suri, Manan, et autres
Publié: (2024)

CodeScout: Contextual Problem Statement Enhancement for Software Agents
par: Suri, Manan, et autres
Publié: (2026)

Beyond Memorization: Distinguishing between Reductive and Epistemic Reasoning in LLMs using Classic Logic Puzzles
par: Gabay, Adi, et autres
Publié: (2026)

TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification
par: Anand, Nishit, et autres
Publié: (2024)

From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning
par: Neema, Nishit, et autres
Publié: (2025)

SteerConf: Steering LLMs for Confidence Elicitation
par: Zhou, Ziang, et autres
Publié: (2025)

FHIRPath-QA: Executable Question Answering over FHIR Electronic Health Records
par: Frew, Michael, et autres
Publié: (2026)