Large Language Models
141 views
DPO
Quick Definition
Alignment method bypassing reward model for preference learning
Full Definition
Direct Preference Optimization, a simplified alignment method that bypasses explicit reward model training.
Examples
LLM alignment, preference learning, simpler RLHF alternative
Related Terms
rlhf
alignment
reward-model
More Large Language Models Terms
Tool Use
Capability of LLMs to call external tools and APIs
Prompt Caching
Storing key-value states for repeated prompt prefixes
Guardrails LLM
Frameworks for monitoring and controlling LLM I/O
Synthetic Data Generation
Using AI to create artificial training data replicating patterns
Multi-Head Attention
Parallel attention operations concatenated for richer representations
Chain-of-Thought Prompting
Technique encouraging step-by-step reasoning in LLMs