Imagen de Portada

A Refined Analysis of Massive Activations in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Owen, Louis, Chowdhury, Nilabhra Roy, Kumar, Abhay, Güra, Fabian
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ZClip: Adaptive Spike Mitigation for LLM Pre-Training
por: Kumar, Abhay, et al.
Publicado: (2025)

Variance Control via Weight Rescaling in LLM Pre-training
por: Owen, Louis, et al.
Publicado: (2025)

BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection
por: Owen, Louis, et al.
Publicado: (2023)

Komodo: A Linguistic Expedition into Indonesia's Regional Languages
por: Owen, Louis, et al.
Publicado: (2024)

Zero-Shot Belief: A Hard Problem for LLMs
por: Murzaku, John, et al.
Publicado: (2025)

Teaching LLMs to Refine with Tools
por: Yu, Dian, et al.
Publicado: (2024)

Detection Without Correction: A Robust Asymmetry in Activation-Based Hallucination Probing
por: Roy, Dip, et al.
Publicado: (2026)

ProvocationProbe: Instigating Hate Speech Dataset from Twitter
por: Kumar, Abhay, et al.
Publicado: (2024)

Massive Activations in Large Language Models
por: Sun, Mingjie, et al.
Publicado: (2024)

OmniVox: Zero-Shot Emotion Recognition with Omni-LLMs
por: Murzaku, John, et al.
Publicado: (2025)

mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs
por: Geigle, Gregor, et al.
Publicado: (2023)

Platypus: Quick, Cheap, and Powerful Refinement of LLMs
por: Lee, Ariel N., et al.
Publicado: (2023)

Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach
por: Chen, Shangfeng, et al.
Publicado: (2024)

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
por: Shi, Zeru, et al.
Publicado: (2026)

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
por: Wang, Qibin, et al.
Publicado: (2025)

MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning
por: Ghosh, Rajarshi, et al.
Publicado: (2025)

The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
por: Sun, Shangwen, et al.
Publicado: (2026)

Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
por: Roh, Youngji, et al.
Publicado: (2026)

MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching
por: Schmidt, Fabian David, et al.
Publicado: (2025)

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

Evaluating LLMs with Multiple Problems at once
por: Wang, Zhengxiang, et al.
Publicado: (2024)

Augmenting In-Context-Learning in LLMs via Automatic Data Labeling and Refinement
por: Shtok, Joseph, et al.
Publicado: (2024)

House of Cards: Massive Weights in LLMs
por: Oh, Jaehoon, et al.
Publicado: (2024)

From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
por: Schiekiera, Louis, et al.
Publicado: (2026)

mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks
por: Beyene, Luel Hagos, et al.
Publicado: (2025)

Unlocking Recursive Thinking of LLMs: Alignment via Refinement
por: Zhang, Haoke, et al.
Publicado: (2025)

Semantic Refinement with LLMs for Graph Representations
por: Thapaliya, Safal, et al.
Publicado: (2025)

Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding
por: Schmidt, Fabian David, et al.
Publicado: (2025)

Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams
por: Lee, Yukyung, et al.
Publicado: (2026)

Non-Contextual BERT or FastText? A Comparative Analysis
por: Shanbhag, Abhay, et al.
Publicado: (2024)

Beyond Performance: Quantifying and Mitigating Label Bias in LLMs
por: Reif, Yuval, et al.
Publicado: (2024)

Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
por: Chowdhury, Arijit Ghosh, et al.
Publicado: (2023)

Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications
por: Liu, Weize, et al.
Publicado: (2024)

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
por: Puerto, Haritz, et al.
Publicado: (2024)

Faithful Summarization of Consumer Health Queries: A Cross-Lingual Framework with LLMs
por: Abrar, Ajwad, et al.
Publicado: (2025)

Improved Generalized Planning with LLMs through Strategy Refinement and Reflection
por: Stein, Katharina, et al.
Publicado: (2025)

VinePPO: Refining Credit Assignment in RL Training of LLMs
por: Kazemnejad, Amirhossein, et al.
Publicado: (2024)

Augmenting NER Datasets with LLMs: Towards Automated and Refined Annotation
por: Naraki, Yuji, et al.
Publicado: (2024)

Contextual Subspace Manifold Projection for Structural Refinement of Large Language Model Representations
por: Wren, Alistair, et al.
Publicado: (2025)

LLMs for Science: Usage for Code Generation and Data Analysis
por: Nejjar, Mohamed, et al.
Publicado: (2023)