AINeutralarXiv – CS AI · Mar 47/102
🧠
LLM Probability Concentration: How Alignment Shrinks the Generative Horizon
Researchers introduce the Branching Factor (BF) metric to measure how alignment tuning reduces output diversity in large language models by concentrating probability distributions. The study reveals that aligned models generate 2-5x less diverse outputs and become more predictable during generation, explaining why alignment reduces sensitivity to decoding strategies and enables more stable Chain-of-Thought reasoning.