Ensembling five Llama-3-8B inferences via the median reduces RMSE by 18.6% versus a single Llama-3-70B run on Yelp sentiment, at less than half the runtime.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
Ensembling five Llama-3-8B inferences via the median reduces RMSE by 18.6% versus a single Llama-3-70B run on Yelp sentiment, at less than half the runtime.