Continuous FunctionStart learning

Foundation Lab

Self-Improvement & Distillation Loops

Makes data generation and model improvement a closed loop

Concept 98 of 100Scaling & AlignmentPhase 13
Inspect equationAll Foundations
#98Self-ImproveScaling & Alignment
key equation
θk+1=arg⁡min⁡θL(θ;Dk∪self-gen)\theta_{k+1} = \arg\min_\theta \mathcal{L}(\theta; D_k \cup \text{self-gen})
Reading map and next steps

Selected Foundation Object

Keep the equation fixed; move through the evidence.

Concept 98 of 100Self-ImproveScaling & Alignment / Phase 13: Cutting-edge 2024-2025 research
Current question

Model bootstraps on its own outputs (filtered by verifier)

θk+1=arg⁡min⁡θL(θ;Dk∪self-gen)\theta_{k+1} = \arg\min_\theta \mathcal{L}(\theta; D_k \cup \text{self-gen})
PredictionCommit before tracing the equation.

Ask what should change under a concrete input, then trace that expectation through the equation.

EvidenceCompare the equation and source.

Use the key equation and canonical papers as the available witnesses, without implying that a runnable panel exists.

InvariantName what survives notation changes.

The useful learning product is the reusable mechanism you can carry into another model, paper, or engineering tradeoff.

Next moveContinue through the atlas.

Use prerequisites, dependents, and semantic links to repair the next gap without leaving the object behind.

Inspect equationBrowse atlasNext foundation

Why It Matters for Modern Models

  • Makes data generation and model improvement a closed loop
  • DeepSeek-R1: RL → reasoning → distill to smaller models
  • Reduces reliance on scarce human labels

What Tutorials Skip

What is still poorly explained in textbooks and papers:

  • Model bootstraps on its own outputs (filtered by verifier)
  • Teacher-student paradigm: large model → small model
  • Risk: distribution shift, mode collapse

Visualization Status

Core Math (Optional Deep Dive)

If you want intuition first, start with the key equation and cited sources. Come back here for the full walkthrough.

Key Equation
θk+1=arg⁡min⁡θL(θ;Dk∪self-gen)\theta_{k+1} = \arg\min_\theta \mathcal{L}(\theta; D_k \cup \text{self-gen})

Iterative self-training loop:

Dk+1=Dk∪{(x,y^):y^∼πθk(⋅∣x)}D_{k+1} = D_k \cup \{(x, \hat{y}) : \hat{y} \sim \pi_{\theta_k}(\cdot|x)\}
θk+1=arg⁡min⁡θE(x,y)∼Dk+1[−log⁡πθ(y∣x)]\theta_{k+1} = \arg\min_\theta \mathbb{E}_{(x,y) \sim D_{k+1}}[-\log \pi_\theta(y|x)]

Distillation: min⁡θsEx[KL(πθt(⋅∣x)∥πθs(⋅∣x))]\min_{\theta_s} \mathbb{E}_x[\mathrm{KL}(\pi_{\theta_t}(\cdot|x) \| \pi_{\theta_s}(\cdot|x))]

Canonical Papers

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Chen et al.2024ICML
Read paper →

Connections

Prerequisites

🧪Distillation⚖RLHF

Next Moves

Choose the next question to carry this object forward.