Image de couverture de livre

Context Structure Reshapes the Representational Geometry of Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hosseini, Eghbal A., Li, Yuxuan, Bahri, Yasaman, Campbell, Declan, Lampinen, Andrew Kyle
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Just-in-time and distributed task representations in language models
par: Li, Yuxuan, et autres
Publié: (2025)

Representational Curvature Modulates Behavioral Uncertainty in Large Language Models
par: King, Jack, et autres
Publié: (2026)

Linear representations in language models can change dramatically over a conversation
par: Lampinen, Andrew Kyle, et autres
Publié: (2026)

Evaluating Spatial Understanding of Large Language Models
par: Yamada, Yutaro, et autres
Publié: (2023)

Distinct Computations Emerge From Compositional Curricula in In-Context Learning
par: Lee, Jin Hwa, et autres
Publié: (2025)

Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation
par: Grabb, Declan, et autres
Publié: (2024)

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
par: Yang, Yukang, et autres
Publié: (2025)

Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models
par: Xu, Ningyu, et autres
Publié: (2026)

Language Models Struggle to Use Representations Learned In-Context
par: Lepori, Michael A., et autres
Publié: (2026)

Measuring Representation Robustness in Large Language Models for Geometry
par: Jawandhia, Vedant, et autres
Publié: (2026)

The Geometry of Representational Failures in Vision Language Models
par: Savietto, Daniele, et autres
Publié: (2026)

Multimodality and Attention Increase Alignment in Natural Language Prediction Between Humans and Computational Models
par: Kewenig, Viktor, et autres
Publié: (2023)

Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently
par: Misra, Kanishka, et autres
Publié: (2024)

Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext
par: Ahuja, Kabir, et autres
Publié: (2026)

Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddings
par: Gonzalez-Gutierrez, Cesar, et autres
Publié: (2025)

ContextGuard: Structured Self-Auditing for Context Learning in Language Models
par: Jin, Hongbo, et autres
Publié: (2026)

Spontaneous Giving and Calculated Greed in Language Models
par: Li, Yuxuan, et autres
Publié: (2025)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
par: Li, Melody Zixuan, et autres
Publié: (2025)

Universal Conceptual Structure in Neural Translation: Probing NLLB-200's Multilingual Geometry
par: Mathewson, Kyle Elliott
Publié: (2026)

Levels of Analysis for Large Language Models
par: Ku, Alexander Y., et autres
Publié: (2025)

AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Large Language Models
par: Jackson, Declan, et autres
Publié: (2025)

The Linear Representation Hypothesis and the Geometry of Large Language Models
par: Park, Kiho, et autres
Publié: (2023)

The Representational Geometry of Number
par: Hu, Zhimin, et autres
Publié: (2026)

Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence
par: Harshavardhan
Publié: (2026)

Evaluating and Enhancing Large Language Models for Conversational Reasoning on Knowledge Graphs
par: Huang, Yuxuan
Publié: (2023)

Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits
par: Huang, Yuxuan
Publié: (2024)

Large Language Models are In-Context Molecule Learners
par: Li, Jiatong, et autres
Publié: (2024)

Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption
par: Wang, Wenxiao, et autres
Publié: (2025)

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
par: Wollschläger, Tom, et autres
Publié: (2025)

The Geometry of Meaning: Perfect Spacetime Representations of Hierarchical Structures
par: Anabalon, Andres, et autres
Publié: (2025)

Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction
par: Kumar, Sreejan, et autres
Publié: (2024)

Language Models Fail to Introspect About Their Knowledge of Language
par: Song, Siyuan, et autres
Publié: (2025)

Cross-Language Bias Examination in Large Language Models
par: Liang, Yuxuan, et autres
Publié: (2025)

On the Predictive Power of Representation Dispersion in Language Models
par: Li, Yanhong, et autres
Publié: (2025)

LooGLE: Can Long-Context Language Models Understand Long Contexts?
par: Li, Jiaqi, et autres
Publié: (2023)

Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds
par: Jeong, Jihoon
Publié: (2026)

The Counterexample Game: Iterated Conceptual Analysis and Repair in Language Models
par: Drucker, Daniel, et autres
Publié: (2026)

RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing
par: Jin, Ruihan, et autres
Publié: (2025)

Decoding-based Regression
par: Song, Xingyou, et autres
Publié: (2025)

Uncovering Emergent Physics Representations Learned In-Context by Large Language Models
par: Song, Yeongwoo, et autres
Publié: (2025)