Random Soft Prompts (RSPs) sampled from the embedding distribution improve Pass@N on reasoning benchmarks by increasing early-stage token diversity without any training.
Prefix-Tuning: Optimizing Continuous Prompts for Generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Noise to Diversity: Random Embedding Injection in LLM Reasoning
Random Soft Prompts (RSPs) sampled from the embedding distribution improve Pass@N on reasoning benchmarks by increasing early-stage token diversity without any training.