paper-with-me

홈 › Papers

States of LLM-generated Texts and Phase Transitions between them

2025-03-08 · Nikolay Mikhaylovskiy

It is known for some time that autocorrelations of words in human-written texts decay according to a power law. Recent works have also shown that the autocorrelations decay in texts generated by LLMs is qualitatively different from the literary texts. Solid state physics tie the autocorrelations decay laws to the states of matter. In this work, we empirically demonstrate that, depending on the temperature parameter, LLMs can generate text that can be classified as solid, critical state or gas.

📄 PDF Abstract BibTeX arXiv:2503.06330

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Critical Phase Transition in Large Language Models

2024-06-08 · Kai Nakaishi, Yoshihiko Nishikawa, Koji Hukushima

Large Language Models (LLMs) have demonstrated impressive performance. To understand their behaviors, we need to consider the fact that LLMs sometimes show qualitative changes. The natural world also presents such change…

Language ModellingLarge Language Model

Attention to Order: Transformers Discover Phase Transitions via Learnability

2025-10-08 · Şener Özönder arxiv

Phase transitions mark qualitative reorganizations of collective behavior, yet identifying their boundaries remains challenging whenever analytic solutions are absent and conventional simulations fail. Here we introduce …

Self-Supervised Learning

Adiabatic Fine-Tuning of Neural Quantum States Enables Detection of Phase Transitions in Weight Space

2025-03-21 · Vinicius Hernandes, Thomas Spriggs, Saqar Khaleefah, Eliska Greplova

Neural quantum states (NQS) have emerged as a powerful tool for approximating quantum wavefunctions using deep learning. While these models achieve remarkable accuracy, understanding how they encode physical information …

Learning to Ball: Composing Policies for Long-Horizon Basketball Moves

2025-09-26 · Pei Xu, Zhen Wu, Ruocheng Wang, Vishnu Sarukkai 외 arxiv

Learning a control policy for a multi-phase, long-horizon task, such as basketball maneuvers, remains challenging for reinforcement learning approaches due to the need for seamless policy composition and transitions betw…

Reinforcement Learning

Topological Persistence Machine of Phase Transitions

2020-04-07 · Quoc Hoan Tran, Mark Chen, Yoshihiko Hasegawa

The study of phase transitions using data-driven approaches is challenging, especially when little prior knowledge of the system is available. Topological data analysis is an emerging framework for characterizing the sha…

Topological Data Analysis