arXiv cs.AI
· Papers
From Noise to Diversity: Random Embedding Injection in LLM Reasoning
arXiv:2605.11936v2 Announce Type: replace Abstract: Recent soft prompt research has tried to improve reasoning by inserting trained vectors into LLM inputs, yet whether the gain comes from the learned content or from the act of injection itself has not been carefully separated. We study Random Soft Prompts (RSPs), whic