From the source
Sakana AI announces a prompting technique called String Seed of Thought (SSoT) that reduces output bias and increases diversity in LLM generations, accepted at ICLR2026.
String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
Research paper
From the source
We discovered a prompting technique named String Seed of Thought (SSoT). The method is simple: instruct the LLM to generate a random string in its own output, then manipulate that string to derive its answer. It requires only a small addition to the prompt and no external random number generator.
sakana.ai