Skip to content
Provenance Brief
Research

Academic or research source. Check the methodology, sample size, and whether it's been replicated.

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors.

arXiv cs.CL · · Paper: ~15 min
Read Original

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs

TLDR

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors.

Artifacts
Paper PDF
Open
O open S save B back M mode