Imagen de Portada

Memorization and Knowledge Injection in Gated LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pan, Xu, Hahami, Ely, Zhang, Zechen, Sompolinsky, Haim
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs
por: Pan, Xu, et al.
Publicado: (2025)

User-Assistant Bias in LLMs
por: Pan, Xu, et al.
Publicado: (2025)

When narrower is better: the narrow width limit of Bayesian parallel branching neural networks
por: Zhang, Zechen, et al.
Publicado: (2024)

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning
por: Xu, Ruoxi, et al.
Publicado: (2025)

SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection
por: Gashkov, Aleksandr, et al.
Publicado: (2025)

Detecting the Disturbance: A Nuanced View of Introspective Abilities in LLMs
por: Hahami, Ely, et al.
Publicado: (2025)

Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs
por: Ranaldi, Federico, et al.
Publicado: (2025)

Memorization vs. Reasoning: Updating LLMs with New Knowledge
por: Li, Aochong Oliver, et al.
Publicado: (2025)

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
por: Sheng, Leheng, et al.
Publicado: (2026)

A General Knowledge Injection Framework for ICD Coding
por: Zhang, Xu, et al.
Publicado: (2025)

Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
por: Ovadia, Oded, et al.
Publicado: (2023)

Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework
por: Luo, Xiaoyu, et al.
Publicado: (2026)

Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models
por: Cao, Boxi, et al.
Publicado: (2023)

$\textit{New News}$: System-2 Fine-tuning for Robust Integration of New Knowledge
por: Park, Core Francisco, et al.
Publicado: (2025)

Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities
por: Luo, Xiaoyu, et al.
Publicado: (2025)

MedMT-Bench: Can LLMs Memorize and Understand Long Multi-Turn Conversations in Medical Scenarios?
por: Yang, Lin, et al.
Publicado: (2026)

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
por: Wang, Changyue, et al.
Publicado: (2025)

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis
por: Djiré, Albérick Euraste, et al.
Publicado: (2025)

Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models
por: Vladika, Juraj, et al.
Publicado: (2025)

Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks
por: Gong, Chang, et al.
Publicado: (2025)

LLMs and Memorization: On Quality and Specificity of Copyright Compliance
por: Mueller, Felix B, et al.
Publicado: (2024)

Data Compressibility Quantifies LLM Memorization
por: Huang, Yizhan, et al.
Publicado: (2025)

Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
por: Wang, Junyang, et al.
Publicado: (2025)

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

How Reliable are LLMs as Knowledge Bases? Re-thinking Facutality and Consistency
por: Zheng, Danna, et al.
Publicado: (2024)

Memorization in Attention-only Transformers
por: Dana, Léo, et al.
Publicado: (2024)

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
por: Lou, Siyu, et al.
Publicado: (2024)

SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Models
por: Xu, Tianhan, et al.
Publicado: (2024)

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
por: Pan, Wenbo, et al.
Publicado: (2025)

Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
por: Kang, Minki, et al.
Publicado: (2024)

SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion
por: Yang, Mengxue, et al.
Publicado: (2025)

bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
por: Ji, Wence, et al.
Publicado: (2025)

Knowledge Capsules: Structured Nonparametric Memory Units for LLMs
por: Ju, Bin, et al.
Publicado: (2026)

Memorization in Fine-Tuned Large Language Models
por: Savine, Danil
Publicado: (2025)

Arithmetic with Language Models: from Memorization to Computation
por: Maltoni, Davide, et al.
Publicado: (2023)

Memorizing Documents with Guidance in Large Language Models
por: Park, Bumjin, et al.
Publicado: (2024)

Context Memorization for Efficient Long Context Generation
por: Okoshi, Yasuyuki, et al.
Publicado: (2026)

Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization
por: Zhang, Zixuan, et al.
Publicado: (2024)

What Layers When: Learning to Skip Compute in LLMs with Residual Gates
por: Laitenberger, Filipe, et al.
Publicado: (2025)

CTourLLM: Enhancing LLMs with Chinese Tourism Knowledge
por: Wei, Qikai, et al.
Publicado: (2024)