FusionRoute augments token-level expert routing with a trainable complementary logit generator to expand the policy class and recover optimal decoding under mild conditions, outperforming prior collaboration and merging methods on reasoning and generation benchmarks.
The perfect blend: Redefining rlhf with mixture of judges.arXiv preprint arXiv:2409.20370
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
citing papers explorer
-
Token-Level LLM Collaboration via FusionRoute
FusionRoute augments token-level expert routing with a trainable complementary logit generator to expand the policy class and recover optimal decoding under mild conditions, outperforming prior collaboration and merging methods on reasoning and generation benchmarks.
-
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.