Large Language Models
288 views
Chain-of-Thought Prompting
Quick Definition
Technique encouraging step-by-step reasoning in LLMs
Full Definition
A technique encouraging LLMs to break down complex problems into sequential reasoning steps.
Examples
math problem solving, complex reasoning, debugging
Related Terms
prompt-engineering
few-shot-learning
More Large Language Models Terms
RLHF
Aligning LLMs with human preferences using reinforcement learning
Flash Attention
Memory-efficient attention using GPU SRAM block computation
Mixture of Experts
Architecture routing tokens to specialized expert sub-networks
Masked Language Model
Training objective predicting randomly masked input tokens
RAG
Enhancing LLMs by retrieving relevant external knowledge
WordPiece
Subword tokenization splitting words into frequent units