Open Models Almanac
Methodsevaluation

specific method · filed under evaluation

Chain-of-thought few-shot prompting

Uses chain-of-thought examples as few-shot evaluation prompts.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See evaluation for the methods filed beside it.

Also called Chain-of-Thought (CoT) examples, Eight-shot chain-of-thought prompting, 8-shot chain-of-thought exact match, 8-shot native chain-of-thought prompting.

sources
2
models
3
labs adopt it
2
strongest
used

Documented in

Evidence

3 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 3

We evaluate MGSM (Shi et al., 2022) using 8-shot native chain-of-thought prompting in Spanish, German, French, Chinese, Japanese, and Russian

usedevaluation onlyin Nemotron 3.5 Super Base and Nemotron 3.5 Lightning BaseNVIDIA
1 more from these models

we evaluate GSM8K (Cobbe et al., 2021) using 8-shot chain-of-thought exact match

usedevaluation onlyin Nemotron 3.5 Super Base and Nemotron 3.5 Lightning BaseNVIDIA
↑