DLLG learns token-level fusion weights for LLM experts from sparse response supervision and outperforms routing, ensembling, and merging baselines on reasoning and code tasks.
Bridging the gap between different vocabularies for llm ensemble.arXiv preprint arXiv:2404.09492
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ME reinterprets LLM ensembling as token-level sampling from a mixture model, enabling single-model invocation per token with claimed mathematical equivalence to full ensembling and measured speedups of 1.78x-2.68x.
citing papers explorer
-
DLLG: Dynamic Logit-Level Gating of LLM Experts
DLLG learns token-level fusion weights for LLM experts from sparse response supervision and outperforms routing, ensembling, and merging baselines on reasoning and code tasks.
-
Rethinking LLM Ensembling from the Perspective of Mixture Models
ME reinterprets LLM ensembling as token-level sampling from a mixture model, enabling single-model invocation per token with claimed mathematical equivalence to full ensembling and measured speedups of 1.78x-2.68x.