Models & Algorithms••🇰🇷 한국어

SDFT: Learning Without Forgetting via Self-Distillation

No complex RL needed. Models teach themselves to learn new skills while preserving existing capabilities.

SDFT: Learning Without Forgetting via Self-Distillation

SDFT: Learning Without Forgetting via Self-Distillation

No complex RL needed. Models teach themselves to learn new skills while preserving existing capabilities.

TL;DR

  • Problem: Traditional SFT causes catastrophic forgetting when learning new tasks
  • Solution: SDFT (Self-Distillation Fine-Tuning)
🔒

Sign in to continue reading

Create a free account to access the full content.

Sign In / Sign Up

Related Posts

Agentic RAG Pipeline — Multi-step Retrieval in Production
Models & Algorithms

Agentic RAG Pipeline — Multi-step Retrieval in Production

Build a full Plan-Retrieve-Evaluate-Synthesize pipeline. Unify vector search, web search, and SQL as agent tools. Add hallucination detection and source grounding.

Self-RAG and Corrective RAG — The Agent Evaluates Its Own Retrieval
Models & Algorithms

Self-RAG and Corrective RAG — The Agent Evaluates Its Own Retrieval

Implement Self-RAG reflection tokens and CRAG quality-based fallback. Build retry/fallback logic with LangGraph conditional edges.

Why Agentic RAG? — Query Routing and Adaptive Retrieval
Models & Algorithms

Why Agentic RAG? — Query Routing and Adaptive Retrieval

Diagnose naive RAG limitations, classify query intent, and route to the optimal retrieval source with LangGraph. Implement adaptive retrieval that skips unnecessary searches.