pith. sign in

Starling-7b: Improving llm helpfulness & harmlessness with rlaif, November 2023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2024 1

verdicts

UNVERDICTED 1

representative citing papers

RouteLLM: Learning to Route LLMs with Preference Data

cs.LG · 2024-06-26 · unverdicted · novelty 6.0

Router models trained on preference data dynamically select between strong and weak LLMs, cutting inference costs by more than 2x on benchmarks with no quality loss and showing transfer to new model pairs.

citing papers explorer

Showing 1 of 1 citing paper.

  • RouteLLM: Learning to Route LLMs with Preference Data cs.LG · 2024-06-26 · unverdicted · none · ref 36

    Router models trained on preference data dynamically select between strong and weak LLMs, cutting inference costs by more than 2x on benchmarks with no quality loss and showing transfer to new model pairs.