- author = "Omar Khattab and Arnav Singhvi and Paridhi Maheshwari and Zhiyuan Zhang and Keshav Santhanam and Sri Vardhamanan A and Saiful Haq and Ashutosh Sharma and Thomas Joshi and Hanna Moazam and Heather Miller and Matei A Zaharia and Christopher Potts",
- title = "DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines",
- booktitle = "NeurIPS 2023 Workshop R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Foundation Models",
- year = "2023",
- editor = "Ananth Balashankar and Saurabh Garg and Jindong Gu and Amrith Setlur and Yao Qin and Aditi Raghunathan and Ahmad Beirami",
- address = "New Orleans, USA",
- month = "15 " # dec,
- keywords = "genetic algorithms, genetic programming: Poster",
-
URL = "
https://neurips.cc/virtual/2023/76693",
-
URL = "https://neurips.cc/virtual/2023/workshop/66517",
- abstract = "The ML community is rapidly exploring techniques for prompting language models (LMs), but existing LM pipelines often rely on hard-coded prompt templates discovered via trial and error. We introduce DSPy, a programming model that abstracts LM pipelines as imperative computation graphs where LMs are invoked through declarative modules. DSPy modules are parameterized so they can learn to apply compositions of prompting, finetuning, augmentation, and reasoning techniques. We design a compiler that will optimize any DSPy pipeline to maximize a given metric. We conduct two case studies and show that a few lines of DSPy allow GPT-3.5 and llama2-13b-chat to self-bootstrap pipelines that outperform standard few-shot prompting and pipelines with expert-created demonstrations.",
-
notes = "See
\cite{khattab2023dspycompilingdeclarativelanguage}
R0-FoMo 2023 https://sites.google.com/view/r0-fomo https://neurips.cc/virtual/2023/workshop/66517",
