Paper Reading Session - DSPy 🤖📈
In this session, Dan will present "DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines," which was led by Omar Khattab at Stanford.
DSPy is a programming model that abstracts LM pipelines as text transformation graphs, i.e. imperative computational graphs where LMs are invoked through declarative modules.
DSPy modules are parameterized, meaning they can learn (by creating and collecting demonstrations) how to apply compositions of prompting, finetuning, augmentation, and reasoning techniques.
A few lines of DSPy allow GPT-3.5 and llama2-13b-chat to self-bootstrap pipelines that outperform standard few-shot prompting (generally by over 25% and 65%, respectively) and pipelines with expert-created demonstrations (by up to 5-46% and 16-40%, respectively).
The paper can be found here.