LangProBe: a Language Programs Benchmark
This addresses the problem of evaluating tradeoffs in language program architectures and optimizers for researchers and practitioners, though it is incremental as it builds on existing paradigms.
The authors tackled the lack of systematic evaluation for language programs by introducing LangProBe, a large-scale benchmark with over 2000 combinations, and found that optimized language programs provide strong cost-quality Pareto improvements over raw model calls.
Composing language models (LMs) into multi-step language programs and automatically optimizing their modular prompts is now a mainstream paradigm for building AI systems, but the tradeoffs in this space have only scarcely been studied before. We introduce LangProBe, the first large-scale benchmark for evaluating the architectures and optimization strategies for language programs, with over 2000 combinations of tasks, architectures, optimizers, and choices of LMs. Using LangProBe, we are the first to study the impact of program architectures and optimizers (and their compositions together and with different models) on tradeoffs of quality and cost. We find that optimized language programs offer strong cost--quality Pareto improvement over raw calls to models, but simultaneously demonstrate that human judgment (or empirical decisions) about which compositions to pursue is still necessary for best performance. We will open source the code and evaluation data for LangProBe.