Image de couverture de livre

Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Patel, Laksh, Shanbhag, Neel
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence 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

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
par: Wang, Xinyi, et autres
Publié: (2024)

Detecting Memorization in Large Language Models
par: Slonski, Eduardo
Publié: (2024)

Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models
par: Bordt, Sebastian, et autres
Publié: (2024)

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
par: Wu, Mingqi, et autres
Publié: (2025)

To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
par: Barbulescu, George-Octavian, et autres
Publié: (2024)

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

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
par: Dong, Yihong, et autres
Publié: (2024)

Bolster Hallucination Detection via Prompt-Guided Data Augmentation
par: Li, Wenyun, et autres
Publié: (2025)

Exploring Memorization in Fine-tuned Language Models
par: Zeng, Shenglai, et autres
Publié: (2023)

Explorations of Self-Repair in Language Models
par: Rushing, Cody, et autres
Publié: (2024)

Real-Time Detection of Hallucinated Entities in Long-Form Generation
par: Obeso, Oscar, et autres
Publié: (2025)

Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI
par: Advani, Laksh
Publié: (2026)

Memorization in In-Context Learning
par: Golchin, Shahriar, et autres
Publié: (2024)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
par: Zhang, Fred, et autres
Publié: (2023)

Skewed Memorization in Large Language Models: Quantification and Decomposition
par: Li, Hao, et autres
Publié: (2025)

An Evaluation on Large Language Model Outputs: Discourse and Memorization
par: de Wynter, Adrian, et autres
Publié: (2023)

Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers
par: Barron, Joshua, et autres
Publié: (2025)

Out-of-Distribution Detection using Synthetic Data Generation
par: Abbas, Momin, et autres
Publié: (2025)

Pruning as a Defense: Reducing Memorization in Large Language Models
par: Gupta, Mansi, et autres
Publié: (2025)

Unintended Memorization of Sensitive Information in Fine-Tuned Language Models
par: Szep, Marton, et autres
Publié: (2026)

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
par: Li, Kenneth, et autres
Publié: (2023)

Socially Aware Synthetic Data Generation for Suicidal Ideation Detection Using Large Language Models
par: Ghanadian, Hamideh, et autres
Publié: (2024)

Memorization: A Close Look at Books
par: Ma, Iris, et autres
Publié: (2025)

Titans: Learning to Memorize at Test Time
par: Behrouz, Ali, et autres
Publié: (2024)

Memorization Dynamics of Fill-in-the-Middle Pretraining
par: von Arx, Tobias, et autres
Publié: (2026)

Memorize and Rank: Elevating Large Language Models for Clinical Diagnosis Prediction
par: Ma, Mingyu Derek, et autres
Publié: (2025)

Memorization-Compression Cycles Improve Generalization
par: Yu, Fangyuan
Publié: (2025)

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion
par: Zaman, Kerem, et autres
Publié: (2023)

ToxiGAN: Toxic Data Augmentation via LLM-Guided Directional Adversarial Generation
par: Li, Peiran, et autres
Publié: (2026)

LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives
par: Shimabucoro, Luísa, et autres
Publié: (2024)

Data-driven Discovery with Large Generative Models
par: Majumder, Bodhisattwa Prasad, et autres
Publié: (2024)

GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
par: Niu, Peizhi, et autres
Publié: (2025)

Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide
par: Szep, Marton, et autres
Publié: (2024)

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
par: Jing, Yi, et autres
Publié: (2026)

Synthetic vs. Gold: The Role of LLM Generated Labels and Data in Cyberbullying Detection
par: Kazemi, Arefeh, et autres
Publié: (2025)

Fill In The Gaps: Model Calibration and Generalization with Synthetic Data
par: Ba, Yang, et autres
Publié: (2024)

Memorization vs. Reasoning: Updating LLMs with New Knowledge
par: Li, Aochong Oliver, et autres
Publié: (2025)

Learning to Detect Language Model Training Data via Active Reconstruction
par: Yin, Junjie Oscar, et autres
Publié: (2026)

To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining
par: Singh, Karan, et autres
Publié: (2026)

Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization
par: Yu, Jing, et autres
Publié: (2025)