most citedDSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

55 citations · 125 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CL20242 cited

Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together

Dilara Soylu, Christopher Potts, Omar Khattab

Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may inv…

cs.IR20241 cited

Prompts as Auto-Optimized Training Hyperparameters: Training Best-in-Class IR Models from Scratch with 10 Gold Labels

Jasper Xian, Saron Samuel, Faraz Khoubsirat +7

We develop a method for training small-scale (under 100M parameter) neural information retrieval models with as few as 10 gold relevance labels. The method depends on generating sy…

cs.IR2024

Backtracing: Retrieving the Cause of the Query

Rose E. Wang, Pawan Wirawarn, Omar Khattab +2

Many online content portals allow users to ask questions to supplement their understanding (e.g., of lectures). While information retrieval (IR) systems may provide answers for suc…

cs.CL20249 cited

Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models

Yijia Shao, Yucheng Jiang, Theodore A. Kanell +3

We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages. This underexplore…

cs.CL20245 cited

In-Context Learning for Extreme Multi-Label Classification

Karel D'Oosterlinck, Omar Khattab, François Remy +3

Multi-label classification problems with thousands of classes are hard to solve with in-context learning alone, as language models (LMs) might lack prior knowledge about the precis…

cs.CL202355 cited

DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

Omar Khattab, Arnav Singhvi, Paridhi Maheshwari +10

The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks. Unfortunately, existing LM pipel…