Imagen de Portada

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hans, Abhimanyu, Wen, Yuxin, Jain, Neel, Kirchenbauer, John, Kazemi, Hamid, Singhania, Prajwal, Singh, Siddharth, Somepalli, Gowthami, Geiping, Jonas, Bhatele, Abhinav, Goldstein, Tom
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers
por: Singh, Siddharth, et al.
Publicado: (2025)

LMD3: Language Model Data Density Dependence
por: Kirchenbauer, John, et al.
Publicado: (2024)

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
por: Geiping, Jonas, et al.
Publicado: (2025)

Speculating Experts Accelerates Inference for Mixture-of-Experts
por: Madan, Vivan, et al.
Publicado: (2026)

FictionalQA: A Dataset for Studying Memorization and Knowledge Acquisition
por: Kirchenbauer, John, et al.
Publicado: (2025)

SolidMark: Evaluating Image Memorization in Generative Models
por: Kriplani, Nicky, et al.
Publicado: (2025)

Power Law Guided Dynamic Sifting for Efficient Attention
por: Koley, Nirav, et al.
Publicado: (2025)

Measuring Style Similarity in Diffusion Models
por: Somepalli, Gowthami, et al.
Publicado: (2024)

Loki: Low-rank Keys for Efficient Sparse Attention
por: Singhania, Prajwal, et al.
Publicado: (2024)

ARGUS: Hallucination and Omission Evaluation in Video-LLMs
por: Rawal, Ruchit, et al.
Publicado: (2025)

A 4D Hybrid Algorithm to Scale Parallel Training to Thousands of GPUs
por: Singh, Siddharth, et al.
Publicado: (2023)

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
por: Hans, Abhimanyu, et al.
Publicado: (2024)

Transformers Can Do Arithmetic with the Right Embeddings
por: McLeish, Sean, et al.
Publicado: (2024)

A Watermark for Large Language Models
por: Kirchenbauer, John, et al.
Publicado: (2023)

What do we learn from inverting CLIP models?
por: Kazemi, Hamid, et al.
Publicado: (2024)

Optimizing Agentic Language Model Inference via Speculative Tool Calls
por: Nichols, Daniel, et al.
Publicado: (2025)

From Pixels to Prose: A Large Dataset of Dense Image Captions
por: Singla, Vasu, et al.
Publicado: (2024)

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
por: Zhao, Kairan, et al.
Publicado: (2026)

Quantifying Cross-Modality Memorization in Vision-Language Models
por: Wen, Yuxin, et al.
Publicado: (2025)

Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
por: Shirkavand, Reza, et al.
Publicado: (2024)

Understanding and Improving Communication Performance in Multi-node LLM Inference
por: Singhania, Prajwal, et al.
Publicado: (2025)

Gemstones: A Model Suite for Multi-Faceted Scaling Laws
por: McLeish, Sean, et al.
Publicado: (2025)

GenQA: Generating Millions of Instructions from a Handful of Prompts
por: Chen, Jiuhai, et al.
Publicado: (2024)

Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training
por: Bonnaire, Tony, et al.
Publicado: (2025)

FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
por: Hayes, Kevin David, et al.
Publicado: (2025)

Coercing LLMs to do and reveal (almost) anything
por: Geiping, Jonas, et al.
Publicado: (2024)

Detecting, Explaining, and Mitigating Memorization in Diffusion Models
por: Wen, Yuxin, et al.
Publicado: (2024)

Mitigating Memorization in LLMs using Activation Steering
por: Suri, Manan, et al.
Publicado: (2025)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
por: Xiong, Alexander, et al.
Publicado: (2025)

CinePile: A Long Video Question Answering Dataset and Benchmark
por: Rawal, Ruchit, et al.
Publicado: (2024)

Learned or Memorized ? Quantifying Memorization Advantage in Code LLMs
por: Euraste, Djiré Albérick, et al.
Publicado: (2026)

Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized
por: Jin, Er, et al.
Publicado: (2025)

HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages
por: Chaturvedi, Aman, et al.
Publicado: (2024)

Mitigating Memorization In Language Models
por: Sakarvadia, Mansi, et al.
Publicado: (2024)

Multi-Token Prediction via Self-Distillation
por: Kirchenbauer, John, et al.
Publicado: (2026)

Zero-Shot Vision Encoder Grafting via LLM Surrogates
por: Yue, Kaiyu, et al.
Publicado: (2025)

Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs
por: Bossy, Thierry, et al.
Publicado: (2025)

GSS: Gated Subspace Steering for Selective Memorization Mitigation in LLMs
por: Zhang, Xuanqi, et al.
Publicado: (2026)

On the Reliability of Watermarks for Large Language Models
por: Kirchenbauer, John, et al.
Publicado: (2023)

Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models
por: Patel, Laksh, et al.
Publicado: (2025)