OSX at Context24: How Well Can GPT Tackle Contexualizing Scientific Figures and Tables

Tosho Hirasawa


Abstract
Identifying the alignment between different parts of a scientific paper is fundamental to scholarly document processing.In the Context24 shared task, participants are given a scientific claim and asked to identify (1) key figures or tables that support the claim and (2) methodological details.While employing a supervised approach to train models on task-specific data is a prevailing strategy for both subtasks, such an approach is not feasible for low-resource domains.Therefore, this paper introduces data-free systems supported by Large Language Models.We propose systems based on GPT-4o and GPT-4-turbo for each task.The experimental results reveal the zero-shot capabilities of GPT-4* in both tasks.
Anthology ID:
2024.sdp-1.31
Volume:
Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Tirthankar Ghosal, Amanpreet Singh, Anita Waard, Philipp Mayr, Aakanksha Naik, Orion Weller, Yoonjoo Lee, Shannon Shen, Yanxia Qin
Venues:
sdp | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
324–331
Language:
URL:
https://aclanthology.org/2024.sdp-1.31
DOI:
Bibkey:
Cite (ACL):
Tosho Hirasawa. 2024. OSX at Context24: How Well Can GPT Tackle Contexualizing Scientific Figures and Tables. In Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024), pages 324–331, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
OSX at Context24: How Well Can GPT Tackle Contexualizing Scientific Figures and Tables (Hirasawa, sdp-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sdp-1.31.pdf