Glossary
Model ensemble
In short
Combining the outputs of several models into one result, so the group performs better than any single member.
Ensembling is an old idea in machine learning: many independent predictors, combined, beat any one of them, because their errors tend to cancel out while their correct answers reinforce each other.
With language models, an ensemble runs the same prompt through several models and combines the answers, whether by merging the best parts, voting, or having one model fuse the rest. The result is steadier and usually better than a single model’s output.
In LLMWeave
A weave is an ensemble in practice. Several models answer, and a final step combines them into one result that keeps the strongest parts of each.
Related terms
Multi-model AI
Using more than one AI model on the same task, instead of relying on a single model for every answer.
Response synthesis
Merging several model answers into one clean result, rather than showing them side by side and making you pick.
Consensus
The points that several models agree on, which tend to be more reliable than any single model’s claims.
Try multi-model on your task
One prompt, several models, one answer. Free to start, no card.
Get started