pith. sign in

Bench-coe: a framework for collaboration of ex- perts from benchmark.arXiv preprint arXiv:2412.04167

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 2

years

2026 1 2025 1

verdicts

UNVERDICTED 2

clear filters

representative citing papers

DLLG: Dynamic Logit-Level Gating of LLM Experts

cs.CL · 2026-06-03 · unverdicted · novelty 6.0

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.

Harnessing Multiple Large Language Models: A Survey on LLM Ensemble

cs.CL · 2025-02-25 · unverdicted · novelty 2.0

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

Showing 1 of 1 citing paper after filters.

  • DLLG: Dynamic Logit-Level Gating of LLM Experts cs.CL · 2026-06-03 · unverdicted · none · ref 22

    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.