Imagen de Portada

Towards Spectroscopy: Susceptibility Clusters in Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gordon, Andrew, Baker, Garrett, Wang, George, Snell, William, van Wingerden, Stan, Murfet, Daniel
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Embryology of a Language Model
por: Wang, George, et al.
Publicado: (2025)

Structural Inference: Interpreting Small Language Models with Susceptibilities
por: Baker, Garrett, et al.
Publicado: (2025)

Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
por: Wang, George, et al.
Publicado: (2024)

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
por: Urdshals, Einar, et al.
Publicado: (2025)

Patterning: The Dual of Interpretability
por: Wang, George, et al.
Publicado: (2026)

Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
por: Elliott, Chris, et al.
Publicado: (2026)

Interpreting Reinforcement Learning Agents with Susceptibilities
por: Elliott, Chris, et al.
Publicado: (2026)

Modes of Sequence Models and Learning Coefficients
por: Chen, Zhongtian, et al.
Publicado: (2025)

Linear Response Estimators for Singular Statistical Models
por: Elliott, Chris, et al.
Publicado: (2026)

In-Context Clustering with Large Language Models
por: Wang, Ying, et al.
Publicado: (2025)

Programs as Singularities
por: Murfet, Daniel, et al.
Publicado: (2025)

Dynamics of Transient Structure in In-Context Linear Regression Transformers
por: Carroll, Liam, et al.
Publicado: (2025)

Loss Landscape Degeneracy and Stagewise Development in Transformers
por: Hoogland, Jesse, et al.
Publicado: (2024)

The Local Learning Coefficient: A Singularity-Aware Complexity Measure
por: Lau, Edmund, et al.
Publicado: (2023)

Stagewise Reinforcement Learning and the Geometry of the Regret Landscape
por: Elliott, Chris, et al.
Publicado: (2026)

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
por: Lehalleur, Simon Pepin, et al.
Publicado: (2025)

Meta-Learning at Scale for Large Language Models via Low-Rank Amortized Bayesian Meta-Learning
por: Zhang, Liyi, et al.
Publicado: (2025)

Large Language Models Are Zero-Shot Time Series Forecasters
por: Gruver, Nate, et al.
Publicado: (2023)

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
por: Snell, Charlie, et al.
Publicado: (2024)

Deep Learning is Not So Mysterious or Different
por: Wilson, Andrew Gordon
Publicado: (2025)

Conformal Prediction as Bayesian Quadrature
por: Snell, Jake C., et al.
Publicado: (2025)

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
por: Marek, Martin, et al.
Publicado: (2026)

SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning
por: Tan, Cheng, et al.
Publicado: (2022)

Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM
por: Fan, Zehao, et al.
Publicado: (2025)

Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
por: Lotfi, Sanae, et al.
Publicado: (2024)

ADNAC: Audio Denoiser using Neural Audio Codec
por: Jimon, Daniel, et al.
Publicado: (2025)

Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
por: Marek, Martin, et al.
Publicado: (2025)

Non-Vacuous Generalization Bounds for Large Language Models
por: Lotfi, Sanae, et al.
Publicado: (2023)

Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering
por: Liu, Yunhui, et al.
Publicado: (2026)

Q-Learning with Clustered-SMART (cSMART) Data: Examining Moderators in the Construction of Clustered Adaptive Interventions
por: Song, Yao, et al.
Publicado: (2025)

Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
por: Zollo, Thomas P., et al.
Publicado: (2023)

Direct Profit Estimation Using Uplift Modeling under Clustered Network Interference
por: Akker, Bram van den
Publicado: (2025)

On the Reproducibility of "FairCLIP: Harnessing Fairness in Vision-Language Learning''
por: Bakker, Hua Chang, et al.
Publicado: (2025)

A Nonparametric Discrete Hawkes Model with a Collapsed Gaussian-Process Prior
por: Brisley, Trinnhallen, et al.
Publicado: (2025)

Towards Multimodal Graph Large Language Model
por: Wang, Xin, et al.
Publicado: (2025)

Predicting Emergent Capabilities by Finetuning
por: Snell, Charlie, et al.
Publicado: (2024)

Machine Learning for Raman Spectroscopy-based Cyber-Marine Fish Biochemical Composition Analysis
por: Zhou, Yun, et al.
Publicado: (2024)

LaTable: Towards Large Tabular Models
por: van Breugel, Boris, et al.
Publicado: (2024)

Coding historical causes of death data with Large Language Models
por: Pedersen, Bjørn, et al.
Publicado: (2024)

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns
por: Baker, Mohammed Abu, et al.
Publicado: (2025)