What question did this study set out to answer?

The aim is to classify lung cancer stages from radiology reports using advanced language models.

April 1, 2026Open Access

SOCIOCOM at the NTCIR-18 RadNLP Main task: Zero-Shot LLM Approaches for Lung Cancer Staging

Key Points

The aim is to classify lung cancer stages from radiology reports using advanced language models.
Utilized GPT-4o model for inference.
Employed prompt engineering techniques to enhance model performance.
Participated in the NTCIR-18 RadNLP 2024 main task for evaluation.
Achieved an accuracy of 0.5648 on Japanese test data.
Demonstrated robustness of the closed-source models in classification tasks.

Abstract

This paper describes our approach to the RadNLP 2024 Maintask as participants of NTCIR-18. The RADNLP 2024 Main Task is to classify the stage of lung cancer from radiology reports. Our approach utilizes GPT-4o for inference, employing prompt engineering techniques. We achieved an accuracy of 0.5648 on the Japanese test data, demonstrating the robustness of closed-source models.

Read Full Paperexternally

Demander à l'IA

Bookmark

View Full Paper