Copertina

Pruning as a Defense: Reducing Memorization in Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gupta, Mansi, Waghela, Nikhar, Gupta, Sarthak, Goel, Shourya, Shanmugavelu, Sanjif
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Scientific Computing with Large Language Models
di: Culver, Christopher, et al.
Pubblicazione: (2024)

Confidence Is All You Need for MI Attacks
di: Sinha, Abhishek, et al.
Pubblicazione: (2023)

Confidence-Modulated Speculative Decoding for Large Language Models
di: Sen, Jaydip, et al.
Pubblicazione: (2025)

Mitigating Memorization In Language Models
di: Sakarvadia, Mansi, et al.
Pubblicazione: (2024)

Detecting Memorization in Large Language Models
di: Slonski, Eduardo
Pubblicazione: (2024)

Skewed Memorization in Large Language Models: Quantification and Decomposition
di: Li, Hao, et al.
Pubblicazione: (2025)

An Evaluation on Large Language Model Outputs: Discourse and Memorization
di: de Wynter, Adrian, et al.
Pubblicazione: (2023)

Large Language Model Pruning
di: Huang, Hanjuan, et al.
Pubblicazione: (2024)

Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization
di: Tang, Zilu, et al.
Pubblicazione: (2025)

Memorize and Rank: Elevating Large Language Models for Clinical Diagnosis Prediction
di: Ma, Mingyu Derek, et al.
Pubblicazione: (2025)

Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning
di: Sakarvadia, Mansi
Pubblicazione: (2024)

Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models
di: Bordt, Sebastian, et al.
Pubblicazione: (2024)

Context-Enhanced Contrastive Search for Improved LLM Text Generation
di: Sen, Jaydip, et al.
Pubblicazione: (2025)

Exploring Memorization in Fine-tuned Language Models
di: Zeng, Shenglai, et al.
Pubblicazione: (2023)

Beware of Calibration Data for Pruning Large Language Models
di: Ji, Yixin, et al.
Pubblicazione: (2024)

COPAL: Continual Pruning in Large Language Generative Models
di: Malla, Srikanth, et al.
Pubblicazione: (2024)

PAT: Pruning-Aware Tuning for Large Language Models
di: Liu, Yijiang, et al.
Pubblicazione: (2024)

Large Language Models for Time Series: A Survey
di: Zhang, Xiyuan, et al.
Pubblicazione: (2024)

To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
di: Barbulescu, George-Octavian, et al.
Pubblicazione: (2024)

Wanda++: Pruning Large Language Models via Regional Gradients
di: Yang, Yifan, et al.
Pubblicazione: (2025)

Pruning Large Language Models by Identifying and Preserving Functional Networks
di: Liu, Yiheng, et al.
Pubblicazione: (2025)

Sample-aware Adaptive Structured Pruning for Large Language Models
di: Kong, Jun, et al.
Pubblicazione: (2025)

Adaptive Pruning for Large Language Models with Structural Importance Awareness
di: Zheng, Haotian, et al.
Pubblicazione: (2024)

A Simple and Effective Pruning Approach for Large Language Models
di: Sun, Mingjie, et al.
Pubblicazione: (2023)

On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models
di: Goel, Naman
Pubblicazione: (2023)

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
di: Wang, Zhepeng, et al.
Pubblicazione: (2024)

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
di: Askari, Hadi, et al.
Pubblicazione: (2025)

Unintended Memorization of Sensitive Information in Fine-Tuned Language Models
di: Szep, Marton, et al.
Pubblicazione: (2026)

SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models
di: Zhu, Hourun, et al.
Pubblicazione: (2025)

On Speculative Decoding for Multimodal Large Language Models
di: Gagrani, Mukul, et al.
Pubblicazione: (2024)

MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation
di: Agarwal, Mehul, et al.
Pubblicazione: (2026)

RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI
di: Gupta, Pankaj, et al.
Pubblicazione: (2026)

MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models
di: Wang, Wentian, et al.
Pubblicazione: (2024)

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models
di: Wang, Ziyan, et al.
Pubblicazione: (2025)

Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
di: Das, Rocktim Jyoti, et al.
Pubblicazione: (2023)

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
di: Xu, Peng, et al.
Pubblicazione: (2024)

Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
di: Wang, Fei, et al.
Pubblicazione: (2024)

IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining
di: Li, Yixiao, et al.
Pubblicazione: (2025)

Languages are Modalities: Cross-Lingual Alignment via Encoder Injection
di: Agarwal, Rajan, et al.
Pubblicazione: (2025)

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
di: Wang, Xinyi, et al.
Pubblicazione: (2024)