Syftr applies multi-objective Bayesian optimization to RAG pipeline search, reporting Pareto frontiers on six benchmarks with 6% accuracy gain at equal cost or 37% cost reduction at equal accuracy versus a LlamaIndex default.
Improving language models by retrieving from trillions of tokens
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
syftr: Pareto-Optimal Generative AI
Syftr applies multi-objective Bayesian optimization to RAG pipeline search, reporting Pareto frontiers on six benchmarks with 6% accuracy gain at equal cost or 37% cost reduction at equal accuracy versus a LlamaIndex default.