Continuous FunctionStart learning

Foundation Lab

Model-Graded Evaluations

Enables scalable safety testing without human bottleneck

Concept 92 of 100Scaling & AlignmentPhase 12
Inspect equationAll Foundations
#92LLM-as-JudgeScaling & Alignment
key equation
μ^=1n∑iE(xi,yi;R)\hat{\mu} = \frac{1}{n} \sum_i E(x_i, y_i; R)
Reading map and next steps

Selected Foundation Object

Keep the equation fixed; move through the evidence.

Concept 92 of 100LLM-as-JudgeScaling & Alignment / Phase 12: Advanced alignment & safety research
Current question

Rubric defines what "good" means: helpfulness, truthfulness, safety

μ^=1n∑iE(xi,yi;R)\hat{\mu} = \frac{1}{n} \sum_i E(x_i, y_i; R)
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

  • Enables scalable safety testing without human bottleneck
  • Fast iteration loops for alignment research
  • Powers modern benchmarks: Chatbot Arena, AlpacaEval

What Tutorials Skip

What is still poorly explained in textbooks and papers:

  • Rubric defines what "good" means: helpfulness, truthfulness, safety
  • Calibration: does model-graded score match human judgment?
  • Position bias: models prefer first option—randomize order

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
μ^=1n∑iE(xi,yi;R)\hat{\mu} = \frac{1}{n} \sum_i E(x_i, y_i; R)

Evaluator model EE scores outputs against rubric RR:

s=E(x,y;R)s = E(x, y; R)

Aggregate:

μ^=1n∑i=1nsi\hat{\mu} = \frac{1}{n} \sum_{i=1}^n s_i

Validate by correlating sis_i with human ratings. Track regressions across model versions.

Canonical Papers

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Zheng et al.2023NeurIPS
Read paper →

Connections

Prerequisites

ℒML/CE/KL🌡️Calibration

Next Moves

Choose the next question to carry this object forward.