✍️
Prompt Engineering
Steering LLMs using CoT, Self-Consistency, Tree of Thoughts, JSON schemas.
123
Prompt Engineering & Reasoning Frameworks
beginner~6hLearn reasoning techniques (CoT, Self-Consistency, Tree of Thoughts), structured JSON prompting, and Verbalized Sampling to prevent mode collapse.
Verbalized Sampling: Fixing LLM Mode Collapse
intermediate~3hA training-free prompting technique that restores an aligned LLM's response diversity by asking it to verbalize a probability distribution over several answers instead of committing to one.
JSON Prompting for LLMs
beginner~2hUsing JSON-structured prompts to get consistent, machine-parseable outputs from LLMs instead of vague natural-language responses.