@inproceedings{frisoni-etal-2024-generate,
title = "To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering",
author = "Frisoni, Giacomo and
Cocchieri, Alessio and
Presepi, Alex and
Moro, Gianluca and
Meng, Zaiqiao",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.533",
doi = "10.18653/v1/2024.acl-long.533",
pages = "9878--9919",
abstract = "Medical open-domain question answering demands substantial access to specialized knowledge. Recent efforts have sought to decouple knowledge from model parameters, counteracting architectural scaling and allowing for training on common low-resource hardware. The retrieve-then-read paradigm has become ubiquitous, with model predictions grounded on relevant knowledge pieces from external repositories such as PubMed, textbooks, and UMLS. An alternative path, still under-explored but made possible by the advent of domain-specific large language models, entails constructing artificial contexts through prompting. As a result, {``}to generate or to retrieve{''} is the modern equivalent of Hamlet{'}s dilemma. This paper presents MedGENIE, the first generate-then-read framework for multiple-choice question answering in medicine. We conduct extensive experiments on MedQA-USMLE, MedMCQA, and MMLU, incorporating a practical perspective by assuming a maximum of 24GB VRAM. MedGENIE sets a new state-of-the-art in the open-book setting of each testbed, allowing a small-scale reader to outcompete zero-shot closed-book 175B baselines while using up to 706x fewer parameters. Our findings reveal that generated passages are more effective than retrieved ones in attaining higher accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="frisoni-etal-2024-generate">
<titleInfo>
<title>To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giacomo</namePart>
<namePart type="family">Frisoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="family">Cocchieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Presepi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gianluca</namePart>
<namePart type="family">Moro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaiqiao</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical open-domain question answering demands substantial access to specialized knowledge. Recent efforts have sought to decouple knowledge from model parameters, counteracting architectural scaling and allowing for training on common low-resource hardware. The retrieve-then-read paradigm has become ubiquitous, with model predictions grounded on relevant knowledge pieces from external repositories such as PubMed, textbooks, and UMLS. An alternative path, still under-explored but made possible by the advent of domain-specific large language models, entails constructing artificial contexts through prompting. As a result, “to generate or to retrieve” is the modern equivalent of Hamlet’s dilemma. This paper presents MedGENIE, the first generate-then-read framework for multiple-choice question answering in medicine. We conduct extensive experiments on MedQA-USMLE, MedMCQA, and MMLU, incorporating a practical perspective by assuming a maximum of 24GB VRAM. MedGENIE sets a new state-of-the-art in the open-book setting of each testbed, allowing a small-scale reader to outcompete zero-shot closed-book 175B baselines while using up to 706x fewer parameters. Our findings reveal that generated passages are more effective than retrieved ones in attaining higher accuracy.</abstract>
<identifier type="citekey">frisoni-etal-2024-generate</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.533</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.533</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>9878</start>
<end>9919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering
%A Frisoni, Giacomo
%A Cocchieri, Alessio
%A Presepi, Alex
%A Moro, Gianluca
%A Meng, Zaiqiao
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F frisoni-etal-2024-generate
%X Medical open-domain question answering demands substantial access to specialized knowledge. Recent efforts have sought to decouple knowledge from model parameters, counteracting architectural scaling and allowing for training on common low-resource hardware. The retrieve-then-read paradigm has become ubiquitous, with model predictions grounded on relevant knowledge pieces from external repositories such as PubMed, textbooks, and UMLS. An alternative path, still under-explored but made possible by the advent of domain-specific large language models, entails constructing artificial contexts through prompting. As a result, “to generate or to retrieve” is the modern equivalent of Hamlet’s dilemma. This paper presents MedGENIE, the first generate-then-read framework for multiple-choice question answering in medicine. We conduct extensive experiments on MedQA-USMLE, MedMCQA, and MMLU, incorporating a practical perspective by assuming a maximum of 24GB VRAM. MedGENIE sets a new state-of-the-art in the open-book setting of each testbed, allowing a small-scale reader to outcompete zero-shot closed-book 175B baselines while using up to 706x fewer parameters. Our findings reveal that generated passages are more effective than retrieved ones in attaining higher accuracy.
%R 10.18653/v1/2024.acl-long.533
%U https://aclanthology.org/2024.acl-long.533
%U https://doi.org/10.18653/v1/2024.acl-long.533
%P 9878-9919
Markdown (Informal)
[To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering](https://aclanthology.org/2024.acl-long.533) (Frisoni et al., ACL 2024)
ACL