Search Results for author:
Found 3 papers, 2 papers with code
Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction
This work shows that useful data can be synthetically generated even for tasks that cannot be solved directly by LLMs: for problems with structured outputs, it is possible to prompt an LLM to perform the task in the reverse direction, by generating plausible input text for a target output structure.
Descartes: Generating Short Descriptions of Wikipedia Articles
Wikipedia is one of the richest knowledge sources on the Web today.
Putting Ridesharing to the Test: Efficient and Scalable Solutions and the Power of Dynamic Vehicle Relocation
We study the optimization of large-scale, real-time ridesharing systems and propose a modular design methodology, Component Algorithms for Ridesharing (CAR).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
