Cover Image

Phase Transitions in the Output Distribution of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Arnold, Julian, Holtorf, Flemming, Schäfer, Frank, Lörch, Niels
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Statistical Mechanics Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment
by: Arnold, Julian, et al.
Published: (2025)

States of LLM-generated Texts and Phase Transitions between them
by: Mikhaylovskiy, Nikolay
Published: (2025)

Grokking as a Falsifiable Finite-Size Transition
by: Bi, Yuda, et al.
Published: (2026)

Machine learning the Ising transition: A comparison between discriminative and generative approaches
by: Zhang, Difei, et al.
Published: (2024)

The Garden of Forking Paths: Observing Dynamic Parameters Distribution in Large Language Models
by: Nicolini, Carlo, et al.
Published: (2024)

Correlation Dimension of Natural Language in a Statistical Manifold
by: Du, Xin, et al.
Published: (2024)

Phase transition on a context-sensitive random language model with short range interactions
by: Toji, Yuma, et al.
Published: (2026)

Random Tree Model of Meaningful Memory
by: Zhong, Weishun, et al.
Published: (2024)

A Theory of LLM Information Susceptibility
by: Song, Zhuo-Yang, et al.
Published: (2026)

Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
by: Ramachandran, Sai Niranjan, et al.
Published: (2026)

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics
by: Sanokowski, Sebastian, et al.
Published: (2025)

IsingFormer: Augmenting Parallel Tempering With Learned Proposals
by: Bunaiyan, Saleh, et al.
Published: (2025)

A Survey on Large Language Model-based Agents for Statistics and Data Science
by: Sun, Maojun, et al.
Published: (2024)

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
by: Hariri, Mohsen, et al.
Published: (2025)

Stochastic Resetting Mitigates Latent Gradient Bias of SGD from Label Noise
by: Bae, Youngkyoung, et al.
Published: (2024)

Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
by: Ashworth, Cassidy, et al.
Published: (2025)

Spontaneous symmetry breaking and Goldstone modes for deep information propagation
by: Iqbal, Nabil, et al.
Published: (2026)

On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective
by: Li, Yuhao, et al.
Published: (2026)

Thermodynamic Irreversibility of Training Algorithms
by: Ziyin, Liu, et al.
Published: (2026)

Reinforcement Learning for Microcanonical Graph Ensemble with Assortativity Constraints
by: Choi, Hoyun, et al.
Published: (2026)

Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models
by: Ramachandran, Sai Niranjan, et al.
Published: (2025)

Berezinskii--Kosterlitz--Thouless transition in a context-sensitive random language model
by: Toji, Yuma, et al.
Published: (2024)

Probing Geometry of Next Token Prediction Using Cumulant Expansion of the Softmax Entropy
by: Viswanathan, Karthik, et al.
Published: (2025)

Neural Total Variation Distance Estimators for Changepoint Detection in News Data
by: Zsolnai, Csaba, et al.
Published: (2025)

SLOT: Structuring the Output of Large Language Models
by: Wang, Darren Yow-Bang, et al.
Published: (2025)

Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
by: Zhang, Yifan F., et al.
Published: (2026)

An Evaluation on Large Language Model Outputs: Discourse and Memorization
by: de Wynter, Adrian, et al.
Published: (2023)

On the Separability of Information in Diffusion Models
by: Premkumar, Akhil
Published: (2025)

Maximum diffusion reinforcement learning
by: Berrueta, Thomas A., et al.
Published: (2023)

Phase Transitions as the Breakdown of Statistical Indistinguishability
by: Narita, Taiyo, et al.
Published: (2026)

A Comparative Study of DSPy Teleprompter Algorithms for Aligning Large Language Models Evaluation Metrics to Human Evaluation
by: Sarmah, Bhaskarjit, et al.
Published: (2024)

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
by: Golowich, Noah, et al.
Published: (2026)

Group-Aware Reinforcement Learning for Output Diversity in Large Language Models
by: Anschel, Oron, et al.
Published: (2025)

Learning to reset in target search problems
by: Muñoz-Gil, Gorka, et al.
Published: (2025)

Learning Kinetic Monte Carlo stochastic dynamics with Deep Generative Adversarial Networks
by: Lanzoni, Daniele, et al.
Published: (2025)

Capturing the Topological Phase Transition and Thermodynamics of the 2D XY Model via Manifold-Aware Score-Based Generative Modeling
by: Jha, Pratyush
Published: (2026)

A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models
by: Cai, Yinpeng, et al.
Published: (2025)

FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data
by: Sinha, Ankur, et al.
Published: (2025)

Eight challenges in developing theory of intelligence
by: Huang, Haiping
Published: (2023)

A Statistical Case Against Empirical Human-AI Alignment
by: Rodemann, Julian, et al.
Published: (2025)