Imagen de Portada

Large language models reorganize representational geometry during in-context learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiong, Hua-Dong, Ji-An, Li, Wilson, Robert C., Lee, Kwonjoon, Wei, Xue-Xin
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Machine Learning Neurons and Cognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Vision-language models learn the geometry of human perceptual space
por: Sanders, Craig, et al.
Publicado: (2025)

Large language models are not about natural language
por: Bolhuis, Johan J., et al.
Publicado: (2025)

Meta predictive learning model of languages in neural circuits
por: Li, Chan, et al.
Publicado: (2023)

Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
por: Ji-An, Li, et al.
Publicado: (2025)

Speaker effects in language comprehension: An integrative model of language and speaker processing
por: Wu, Hanlin, et al.
Publicado: (2024)

HDGL: A hierarchical dynamic graph representation learning model for brain disorder classification
por: Jalali, Parnian, et al.
Publicado: (2023)

Category learning in deep neural networks: Information content and geometry of internal representations
por: Bonnasse-Gahot, Laurent, et al.
Publicado: (2025)

Prediction horizon shapes representations in predictive learning
por: Ratzon, Aviv, et al.
Publicado: (2025)

Generative causal testing to bridge data-driven models and scientific theories in language neuroscience
por: Antonello, Richard, et al.
Publicado: (2024)

Integrating large language models and active inference to understand eye movements in reading and dyslexia
por: Donnarumma, Francesco, et al.
Publicado: (2023)

Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment
por: Wu, Hanlin, et al.
Publicado: (2025)

Predictive and feedback signals differently shape the formation of group-level and individualized language representations
por: Yang, Shuguang, et al.
Publicado: (2026)

Linguistic properties and model scale in brain encoding: from small to compressed language models
por: Oota, Subba Reddy, et al.
Publicado: (2026)

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
por: Oota, Subba Reddy, et al.
Publicado: (2026)

Multifaceted neural representation of words in naturalistic language
por: Yang, Xuan, et al.
Publicado: (2026)

Hebbian learning the local structure of language
por: Eugenio, P. Myles
Publicado: (2025)

Toward the biological model of the hippocampus as the successor representation agent
por: Lee, Hyunsu
Publicado: (2020)

Emergence of psychopathological computations in large language models
por: Lee, Soo Yong, et al.
Publicado: (2025)

The time course of visuo-semantic representations in the human brain is captured by combining vision and language models
por: Rong, Boyan, et al.
Publicado: (2025)

Relational reasoning and inductive bias in transformers and large language models
por: Geerts, Jesse, et al.
Publicado: (2025)

A foundation model of vision, audition, and language for in-silico neuroscience
por: d'Ascoli, Stéphane, et al.
Publicado: (2026)

Unsupervised learning of multiscale switching dynamical system models from multimodal neural data
por: Kim, DongKyu, et al.
Publicado: (2025)

Brain-to-Text Benchmark '24: Lessons Learned
por: Willett, Francis R., et al.
Publicado: (2024)

Dissociating model architectures from inference computations
por: Sajid, Noor, et al.
Publicado: (2025)

Clarifying the conceptual dimensions of representation in neuroscience
por: Pohl, Stephan, et al.
Publicado: (2024)

Probabilistic adaptation of language comprehension for individual speakers: evidence from neural oscillations
por: Wu, Hanlin, et al.
Publicado: (2025)

Visual representations in the human brain are aligned with large language models
por: Doerig, Adrien, et al.
Publicado: (2022)

Speech language models lack important brain-relevant semantics
por: Oota, Subba Reddy, et al.
Publicado: (2023)

Large language models and the entropy of English
por: Scheibner, Colin, et al.
Publicado: (2025)

Unsupervised discovery of the shared and private geometry in multi-view data
por: Koukuntla, Sai, et al.
Publicado: (2024)

Representation biases: will we achieve complete understanding by analyzing representations?
por: Lampinen, Andrew Kyle, et al.
Publicado: (2025)

Interpretable statistical representations of neural population dynamics and geometry
por: Gosztolai, Adam, et al.
Publicado: (2023)

Quantifying task-relevant representational similarity using decision variable correlation
por: Qian, Yu Eric, et al.
Publicado: (2025)

Learning to combine top-down context and feed-forward representations under ambiguity with apical and basal dendrites
por: Islah, Nizar, et al.
Publicado: (2023)

Sparks of cognitive flexibility: self-guided context inference for flexible stimulus-response mapping by attentional routing
por: Sommers, Rowan P., et al.
Publicado: (2025)

Beyond Human-Like Processing: Large Language Models Perform Equivalently on Forward and Backward Scientific Text
por: Luo, Xiaoliang, et al.
Publicado: (2024)

Emergence of Grid-like Representations by Training Recurrent Networks with Conformal Normalization
por: Xu, Dehong, et al.
Publicado: (2023)

On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position Embedding
por: Xu, Dehong, et al.
Publicado: (2024)

On periodic distributed representations using Fourier embeddings
por: Chouinard, Jakeb
Publicado: (2026)

Summary statistics of learning link changing neural representations to behavior
por: Zavatone-Veth, Jacob A., et al.
Publicado: (2025)