String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
pub.sakana.ai · 2,959 words · saved by 1 readers
SSoT: A simple prompting method that enables LLMs to generate distribution-faithful and diverse outputs by first generating a random string.
This page requires Javascript. Please enable it to view the website. tl;dr We introduce String Seed of Thought (SSoT), a simple prompting method that substantially improves LLMs' ability to follow probabilistic instructions and generate diverse outputs. SSoT instructs the LLM to first generate a random string, then manipulate it to derive the answer. The method requires no additional training or external tools, only a change to the prompt. SSoT instructs the LLM to (1) generate a random string to create a seed, then (2) manipulate it to generate an output. This simple two-stage prompt…
saved by
related reading
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- The Shape of AI | UX Patterns for Artificial Intelligence Designshapeof.ai
- Prompt Injection as Role Confusionrole-confusion.github.io
- Prompting best practicesdocs.anthropic.com
- Chain-of-Thought Promptinglearnprompting.org
- GitHub - f/prompts.chat: f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.github.com
- Prompt generation | OpenAI APIplatform.openai.com
- PromptLayer — Prompt Management, Evals & Observabilitypromptlayer.com
- Everything I'll forget about prompting LLMsolickel.com
- Prompt engineering | OpenAI APIplatform.openai.com
- LLM Settings | Prompt Engineering Guidepromptingguide.ai