Copertina

Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Datta, Shrestha, Liu, Hongfu, Chhabra, Anshuman
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models
di: Chhabra, Anshuman, et al.
Pubblicazione: (2024)

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

First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation
di: Vitel, Dmytro, et al.
Pubblicazione: (2025)

Low Rank Gradients and Where to Find Them
di: Sonthalia, Rishi, et al.
Pubblicazione: (2025)

Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
di: Amaefuna, Theophilus, et al.
Pubblicazione: (2026)

On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
di: Shrestha, Safal, et al.
Pubblicazione: (2026)

Fantastic Pretraining Optimizers and Where to Find Them
di: Wen, Kaiyue, et al.
Pubblicazione: (2025)

Layer-Aware Influence for Online Data Valuation Estimation
di: Yang, Ziao, et al.
Pubblicazione: (2025)

Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
di: Nahin, Shahriar Kabir, et al.
Pubblicazione: (2025)

Fantastic Bugs and Where to Find Them in AI Benchmarks
di: Truong, Sang, et al.
Pubblicazione: (2025)

Calibrated Language Models and How to Find Them with Label Smoothing
di: Huang, Jerry, et al.
Pubblicazione: (2025)

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
di: Bui, Anh, et al.
Pubblicazione: (2025)

Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
di: Zhang, Zhenyu, et al.
Pubblicazione: (2025)

Latent Knowledge Scalpel: Precise and Massive Knowledge Editing for Large Language Models
di: Liu, Xin, et al.
Pubblicazione: (2025)

Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
di: Monjur, Ocean, et al.
Pubblicazione: (2026)

What Cohort INRs Encode and Where to Freeze Them
di: Sideri-Lampretsa, Vasiliki, et al.
Pubblicazione: (2026)

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
di: Chuang, Yung-Sung, et al.
Pubblicazione: (2023)

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
di: Chhabra, Anshuman, et al.
Pubblicazione: (2025)

LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?
di: Tamo, J. Ben, et al.
Pubblicazione: (2026)

Knowledge Fusion of Large Language Models Via Modular SkillPacks
di: Du, Guodong, et al.
Pubblicazione: (2025)

Knowledge Editing on Black-box Large Language Models
di: Song, Xiaoshuai, et al.
Pubblicazione: (2024)

The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
di: Lu, Yao, et al.
Pubblicazione: (2025)

Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training
di: Nepal, Aadim, et al.
Pubblicazione: (2025)

TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training
di: Zhang, Ruijie, et al.
Pubblicazione: (2026)

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
di: Jin, Mingyu, et al.
Pubblicazione: (2024)

Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients
di: Nguyen, Minh Duong, et al.
Pubblicazione: (2024)

Layer by Layer: Uncovering Hidden Representations in Language Models
di: Skean, Oscar, et al.
Pubblicazione: (2025)

Unraveling Indirect In-Context Learning Using Influence Functions
di: Askari, Hadi, et al.
Pubblicazione: (2025)

Gradient Boosting within a Single Attention Layer
di: Sargolzaei, Saleh
Pubblicazione: (2026)

Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)
di: Prinster, Drew, et al.
Pubblicazione: (2024)

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
di: Hu, Jerry Yao-Chieh, et al.
Pubblicazione: (2024)

Understanding and Guiding Layer Placement in Parameter-Efficient Fine-Tuning of Large Language Models
di: Xu, Yichen, et al.
Pubblicazione: (2026)

LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
di: Veldanda, Akshaj Kumar, et al.
Pubblicazione: (2024)

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone
di: Hassanpour, Negar, et al.
Pubblicazione: (2025)

K-Edit: Language Model Editing with Contextual Knowledge Awareness
di: Markowitz, Elan, et al.
Pubblicazione: (2025)

Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
di: Bandarkar, Lucas, et al.
Pubblicazione: (2024)

CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression
di: Kautsar, Muchammad Daniyal, et al.
Pubblicazione: (2025)

Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles
di: Wei, Qingyan, et al.
Pubblicazione: (2025)

Editing Conceptual Knowledge for Large Language Models
di: Wang, Xiaohan, et al.
Pubblicazione: (2024)

L$^3$: Large Lookup Layers
di: Tseng, Albert, et al.
Pubblicazione: (2026)