Equation 8 · Part 4 · Comparing the Main Approaches to Training Data and Synthetic Data
=
=
What this part means
The expressions on both sides represent the same quantity under the stated assumptions.
Its job in the formula
The equals sign connects the complete expression on the left with the complete expression on the right. Both sides must have compatible units.
Full expression→=→Article meaning
The passage around this formula
Rejection sampling generates multiple candidate completions per prompt from a model and keeps only the ones a separate scoring step accepts, using the survivors as supervised fine-tuning data. Llama 2’s RLHF pipeline used exactly this for its first four rounds, generating candidates from the 70-billion-parameter model, scoring them against a trained reward model, and only introducing proximal policy optimisation as a second mechanism in later rounds once the returns from sampling alone began to taper [ 6 ] . A second, independent demonstration in mathematical reasoning makes the mechanism even more explicit: rejection sampling fine-tuning collects correct reasoning paths directly from a…
Learn the underlying idea
An equals sign says that the expression on its left and the expression on its right have the same value under the stated definitions and assumptions.
Open the illustrated equality: what the equals sign claims guide →
Sources cited in the surrounding passage
- [6] Llama 2: Open Foundation and Fine-Tuned Chat Models ↗
- [7] Scaling Relationship on Learning Mathematical Reasoning with Large Language Models ↗
These citations provide research context; check each source for the exact claim it supports.