#phase-transition News & Analysis

3 articles tagged with #phase-transition. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBullisharXiv – CS AI · Jun 27/10

🧠

Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling

Researchers discover that language models exhibit a phase transition between reasoning and truthfulness capabilities at around 3.5B parameters, where smaller models show anticorrelated capabilities while larger ones show cooperation. This hidden alignment transition is invisible to standard loss curves but can be diagnosed from public benchmarks alone, and a proof-of-concept intervention demonstrates that adding a truth-direction vector can correct misaligned outputs without retraining.

🧠 Llama

AIBearisharXiv – CS AI · May 117/10

🧠

How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem

A new empirical study evaluates how Large Language Models perform on the Equivalence Class Problem, a simple yet computationally demanding long-chain reasoning task. The research reveals that non-reasoning LLMs fail entirely at the task, while reasoning-capable models perform significantly better but still struggle with complete accuracy, with performance patterns differing based on problem complexity metrics.

AINeutralarXiv – CS AI · Apr 77/10

🧠

Grokking as Dimensional Phase Transition in Neural Networks

Researchers identify neural network 'grokking' as a dimensional phase transition where effective dimensionality shifts from sub-diffusive to super-diffusive during the memorization-to-generalization transition. The study reveals this transition reflects gradient field geometry rather than network architecture, offering new insights into overparameterized network trainability.

$AVAX