Cover Image

Latent Trajectory Dynamics in Large Language Models: A Manifold Evolution Framework with Empirical Validation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yukun, Dong, Qi, Li, Mengkang
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Scale Manifold Alignment for Interpreting Large Language Models: A Unified Information-Geometric Framework
by: Zhang, Yukun, et al.
Published: (2025)

Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models
by: Zhang, Yukun, et al.
Published: (2025)

A Novel Self-Evolution Framework for Large Language Models
by: Sun, Haoran, et al.
Published: (2025)

Emergent Hierarchical Structure in Large Language Models: An Information-Theoretic Framework for Multi-Scale Representation
by: Zhang, Yukin, et al.
Published: (2025)

An Empirical Analysis of Uncertainty in Large Language Model Evaluations
by: Xie, Qiujie, et al.
Published: (2025)

Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
by: Li, Zirui, et al.
Published: (2026)

Text2World: Benchmarking Large Language Models for Symbolic World Model Generation
by: Hu, Mengkang, et al.
Published: (2025)

Electronic Circuit Principles of Large Language Models
by: Chen, Qiguang, et al.
Published: (2025)

An Empirical Study on Prompt Compression for Large Language Models
by: Zhang, Zheng, et al.
Published: (2025)

Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models
by: Liu, Xukai, et al.
Published: (2026)

Unveiling LLM Mechanisms Through Neural ODEs and Control Theory
by: Zhang, Yukun, et al.
Published: (2024)

HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
by: Hu, Mengkang, et al.
Published: (2024)

ChemATP: A Training-Free Chemical Reasoning Framework for Large Language Models
by: Zhang, Mingxu, et al.
Published: (2025)

A Survey on Self-Evolution of Large Language Models
by: Tao, Zhengwei, et al.
Published: (2024)

Dynamic Topic Evolution with Temporal Decay and Attention in Large Language Models
by: Wu, Di, et al.
Published: (2025)

Can Large Language Models Understand DL-Lite Ontologies? An Empirical Study
by: Wang, Keyu, et al.
Published: (2024)

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
by: Chen, Qiguang, et al.
Published: (2025)

Large Language Models Explore by Latent Distilling
by: Zeng, Yuanhao, et al.
Published: (2026)

Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
by: Wang, Xinyuan, et al.
Published: (2025)

Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models
by: Chen, Hao, et al.
Published: (2026)

Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models
by: Xu, Fangzhi, et al.
Published: (2024)

Empirical Analysis of Dialogue Relation Extraction with Large Language Models
by: Li, Guozheng, et al.
Published: (2024)

Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
by: Hu, Zhengyu, et al.
Published: (2025)

To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts
by: Huang, Yukun, et al.
Published: (2024)

An Empirical Analysis on Large Language Models in Debate Evaluation
by: Liu, Xinyi, et al.
Published: (2024)

GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models
by: Tang, Kunsheng, et al.
Published: (2024)

Fake News Detection and Manipulation Reasoning via Large Vision-Language Models
by: Jin, Ruihan, et al.
Published: (2024)

On the Failure of Latent State Persistence in Large Language Models
by: Huang, Jen-tse, et al.
Published: (2025)

Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models
by: Tu, Mingchen, et al.
Published: (2025)

Reasoning Beyond Chain-of-Thought: A Latent Computational Mode in Large Language Models
by: He, Zhenghao, et al.
Published: (2026)

DLP: Dynamic Layerwise Pruning in Large Language Models
by: Chen, Yuli, et al.
Published: (2025)

An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarios
by: Li, Zongjie, et al.
Published: (2024)

An Empirical Study of Many-to-Many Summarization with Large Language Models
by: Wang, Jiaan, et al.
Published: (2025)

An Empirical Evaluation of Large Language Models on Consumer Health Questions
by: Abrar, Moaiz, et al.
Published: (2024)

Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning
by: Song, Rui, et al.
Published: (2026)

Self-Boosting Large Language Models with Synthetic Preference Data
by: Dong, Qingxiu, et al.
Published: (2024)

Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements
by: Qian, Yushan, et al.
Published: (2023)

A Framework for Real-time Safeguarding the Text Generation of Large Language Model
by: Dong, Ximing, et al.
Published: (2024)

Unlocking the Working Memory of Large Language Models for Latent Reasoning
by: Aichberger, Lukas, et al.
Published: (2026)

On Effects of Steering Latent Representation for Large Language Model Unlearning
by: Huu-Tien, Dang, et al.
Published: (2024)