대규모 언어 모델을 활용한 한국어 문맥 기반 문장 순서 예측 모형

초록

Sentence order critically affects textual coherence and comprehension, yet real-world data often exhibit disrupted ordering. This study investigates Korean context-aware sentence ordering with Large Language Models, comparing three approaches—Pairwise, Sequence, and Global—through fine-tuning of pretrained models such as KLUE-BERT, KoELECTRA, KLUE-RoBERTa, and T5. Experiments were conducted on the DACON Context-Aware Sentence Ordering AI Competition dataset, comprising 7,350 training and 1,780 test samples. The Pairwise approach effectively captured local sentence relations but failed to model global coherence. The Sequence approach provided an intuitive framework, yet its performance degraded with longer inputs due to overfitting. By contrast, the Global approach, formulated as a classification problem over all permutations, exhibited the most consistent and superior results. Notably, the KLUE-RoBERTa–based Global model achieved the highest score of 83.71% on the private leaderboard.

키워드