To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering
Giacomo Frisoni, Alessio Cocchieri, Alex Presepi, Gianluca Moro, Zaiqiao Meng
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.- Anthology ID:
- 2024.acl-long.533
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9878–9919
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.533
- DOI:
- 10.18653/v1/2024.acl-long.533
- Cite (ACL):
- Giacomo Frisoni, Alessio Cocchieri, Alex Presepi, Gianluca Moro, and Zaiqiao Meng. 2024. To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9878–9919, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering (Frisoni et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2024.acl-long.533.pdf