Imagen de Portada

Deep Language Geometry: Constructing a Metric Space from LLM Weights

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shamrai, Maksym, Hamolia, Vladyslav
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GUIrilla: A Scalable Framework for Automated Desktop UI Exploration
por: Garkot, Sofiya, et al.
Publicado: (2025)

Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
por: Li, Zihao, et al.
Publicado: (2024)

Weight-of-Thought Reasoning: Exploring Neural Network Weights for Enhanced LLM Reasoning
por: Punjwani, Saif, et al.
Publicado: (2025)

Does Refusal Training in LLMs Generalize to the Past Tense?
por: Andriushchenko, Maksym, et al.
Publicado: (2024)

Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation
por: Alam, Firoj, et al.
Publicado: (2026)

DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
por: DeepSeek-AI, et al.
Publicado: (2024)

Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
por: He, Zhonghao, et al.
Publicado: (2025)

Geometry of Decision Making in Language Models
por: Joshi, Abhinav, et al.
Publicado: (2025)

Visualizing Uncertainty in Translation Tasks: An Evaluation of LLM Performance and Confidence Metrics
por: Park, Jin Hyun, et al.
Publicado: (2025)

Self-Refinement of Language Models from External Proxy Metrics Feedback
por: Ramji, Keshav, et al.
Publicado: (2024)

An LLM Feature-based Framework for Dialogue Constructiveness Assessment
por: Zhou, Lexin, et al.
Publicado: (2024)

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
por: Sun, Lihao, et al.
Publicado: (2026)

Screen2AX: Vision-Based Approach for Automatic macOS Accessibility Generation
por: Muryn, Viktor, et al.
Publicado: (2025)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
por: Li, Melody Zixuan, et al.
Publicado: (2025)

Capability-Based Scaling Trends for LLM-Based Red-Teaming
por: Panfilov, Alexander, et al.
Publicado: (2025)

Learning to Interpret Weight Differences in Language Models
por: Goel, Avichal, et al.
Publicado: (2025)

Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning
por: Wang, Fangxin, et al.
Publicado: (2026)

Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
por: Albanese, Federico, et al.
Publicado: (2026)

The Geometry of Categorical and Hierarchical Concepts in Large Language Models
por: Park, Kiho, et al.
Publicado: (2024)

The Linear Representation Hypothesis and the Geometry of Large Language Models
por: Park, Kiho, et al.
Publicado: (2023)

Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
por: Wang, Dongwei, et al.
Publicado: (2024)

Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling
por: Lipkin, Benjamin, et al.
Publicado: (2025)

Perturbation Analysis of Singular Values in Concatenated Matrices
por: Shamrai, Maksym
Publicado: (2025)

Balanced Accuracy: The Right Metric for Evaluating LLM Judges -- Explained through Youden's J statistic
por: Collot, Stephane, et al.
Publicado: (2025)

Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction
por: Zhang, Bowen, et al.
Publicado: (2024)

PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models
por: Zhao, Chenzhuo, et al.
Publicado: (2025)

Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training
por: Krajewski, Jakub, et al.
Publicado: (2025)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
por: Zhang, Fred, et al.
Publicado: (2023)

Graph-based Uncertainty Metrics for Long-form Language Model Outputs
por: Jiang, Mingjian, et al.
Publicado: (2024)

Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training
por: Bergsma, Shane, et al.
Publicado: (2025)

GWQ: Gradient-Aware Weight Quantization for Large Language Models
por: Shao, Yihua, et al.
Publicado: (2024)

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
por: Zhang, Pingyue, et al.
Publicado: (2026)

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
por: Wollschläger, Tom, et al.
Publicado: (2025)

Is In-Context Learning Sufficient for Instruction Following in LLMs?
por: Zhao, Hao, et al.
Publicado: (2024)

The Geometry of Reasoning: Flowing Logics in Representation Space
por: Zhou, Yufa, et al.
Publicado: (2025)

Language Models Represent Space and Time
por: Gurnee, Wes, et al.
Publicado: (2023)

CORE-KG: An LLM-Driven Knowledge Graph Construction Framework for Human Smuggling Networks
por: Meher, Dipak, et al.
Publicado: (2025)

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
por: Balestriero, Randall, et al.
Publicado: (2023)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
por: Andriushchenko, Maksym, et al.
Publicado: (2024)

SpaceByte: Towards Deleting Tokenization from Large Language Modeling
por: Slagle, Kevin
Publicado: (2024)