April 15, 2024, 4:47 a.m. | Juraj Vladika, Florian Matthes

cs.CL updates on arXiv.org arxiv.org

arXiv:2404.08359v1 Announce Type: new
Abstract: In today's digital world, seeking answers to health questions on the Internet is a common practice. However, existing question answering (QA) systems often rely on using pre-selected and annotated evidence documents, thus making them inadequate for addressing novel questions. Our study focuses on the open-domain QA setting, where the key challenge is to first uncover relevant evidence in large knowledge bases. By utilizing the common retrieve-then-read QA pipeline and PubMed as a trustworthy collection of …

abstract arxiv cs.ai cs.cl cs.ir digital digital world documents domain evidence health however improving internet making novel practice question question answering questions retrieval study systems them type world

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US