FlowCompile performs compile-time design space exploration on structured LLM workflows to produce reusable high-quality configuration sets that outperform routing baselines with up to 6.4x speedup.
and Salakhutdinov, Ruslan and Manning, Christopher D
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
MultiHop-RAG is a new benchmark dataset demonstrating that existing retrieval-augmented generation systems perform poorly on multi-hop queries requiring retrieval and reasoning over multiple evidence pieces.
A conformal procedure for CoT replaces majority voting with weighted aggregation and calibrates abstention to guarantee low confident-error rates, achieving 90.1% selective accuracy on GSM8K by abstaining on under 5% of cases.
citing papers explorer
-
FlowCompile: An Optimizing Compiler for Structured LLM Workflows
FlowCompile performs compile-time design space exploration on structured LLM workflows to produce reusable high-quality configuration sets that outperform routing baselines with up to 6.4x speedup.
-
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
MultiHop-RAG is a new benchmark dataset demonstrating that existing retrieval-augmented generation systems perform poorly on multi-hop queries requiring retrieval and reasoning over multiple evidence pieces.
-
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
A conformal procedure for CoT replaces majority voting with weighted aggregation and calibrates abstention to guarantee low confident-error rates, achieving 90.1% selective accuracy on GSM8K by abstaining on under 5% of cases.