AINeutralarXiv – CS AI · Mar 37/104
🧠
How Do LLMs Use Their Depth?
New research reveals that large language models use a "Guess-then-Refine" framework, starting with high-frequency token predictions in early layers and refining them with contextual information in deeper layers. The study provides detailed insights into layer-wise computation dynamics through multiple-choice tasks, fact recall analysis, and part-of-speech predictions.