A well-tuned kNN router matches or exceeds state-of-the-art learned routers on new standardized benchmarks spanning instruction, QA, reasoning, and the first multi-modal visual routing dataset, due to locality of model performance in embedding space.
Routoo: Learning to route to large language models effectively.arXiv preprint arXiv:2401.13979
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
An approximate greedy router for hybrid PDE solvers that mimics optimal selection without true error access and shows faster, more stable error reduction on test equations.
DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.
A systematic survey of LLM ensemble methods organized into a taxonomy of ensemble-before-inference, ensemble-during-inference, and ensemble-after-inference stages, with review of benchmarks, applications, and future directions.
citing papers explorer
-
A Greedy PDE Router for Blending Neural Operators and Classical Methods
An approximate greedy router for hybrid PDE solvers that mimics optimal selection without true error access and shows faster, more stable error reduction on test equations.
-
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing
DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.
-
Harnessing Multiple Large Language Models: A Survey on LLM Ensemble
A systematic survey of LLM ensemble methods organized into a taxonomy of ensemble-before-inference, ensemble-during-inference, and ensemble-after-inference stages, with review of benchmarks, applications, and future directions.